Merge branch 'master' into use-other-downloaders
This commit is contained in:
Rogério Brito
commit
adafe3a865
16
README.md
16
README.md
@ -120,18 +120,20 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
--max-quality FORMAT highest quality format to download
|
||||
-F, --list-formats list all available formats (currently youtube
|
||||
only)
|
||||
|
||||
## Subtitle Options:
|
||||
--write-sub write subtitle file (currently youtube only)
|
||||
--write-auto-sub write automatic subtitle file (currently youtube
|
||||
only)
|
||||
--only-sub [deprecated] alias of --skip-download
|
||||
--all-subs downloads all the available subtitles of the
|
||||
video (currently youtube only)
|
||||
video
|
||||
--list-subs lists all available subtitles for the video
|
||||
(currently youtube only)
|
||||
--sub-format FORMAT subtitle format [srt/sbv/vtt] (default=srt)
|
||||
(currently youtube only)
|
||||
--sub-lang LANG language of the subtitles to download (optional)
|
||||
use IETF language tags like 'en'
|
||||
--sub-format FORMAT subtitle format (default=srt) ([sbv/vtt] youtube
|
||||
only)
|
||||
--sub-lang LANGS languages of the subtitles to download (optional)
|
||||
separated by commas, use IETF language tags like
|
||||
'en,pt'
|
||||
|
||||
## Authentication Options:
|
||||
-u, --username USERNAME account username
|
||||
@ -153,6 +155,8 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
processing; the video is erased by default
|
||||
--no-post-overwrites do not overwrite post-processed files; the post-
|
||||
processed files are overwritten by default
|
||||
--embed-subs embed subtitles in the video (only for mp4
|
||||
videos)
|
||||
|
||||
# CONFIGURATION
|
||||
|
||||
|
||||
@ -6,28 +6,32 @@ import hashlib
|
||||
import urllib.request
|
||||
|
||||
if len(sys.argv) <= 1:
|
||||
print('Specify the version number as parameter')
|
||||
sys.exit()
|
||||
print('Specify the version number as parameter')
|
||||
sys.exit()
|
||||
version = sys.argv[1]
|
||||
|
||||
with open('update/LATEST_VERSION', 'w') as f:
|
||||
f.write(version)
|
||||
f.write(version)
|
||||
|
||||
versions_info = json.load(open('update/versions.json'))
|
||||
if 'signature' in versions_info:
|
||||
del versions_info['signature']
|
||||
del versions_info['signature']
|
||||
|
||||
new_version = {}
|
||||
|
||||
filenames = {'bin': 'youtube-dl', 'exe': 'youtube-dl.exe', 'tar': 'youtube-dl-%s.tar.gz' % version}
|
||||
filenames = {
|
||||
'bin': 'youtube-dl',
|
||||
'exe': 'youtube-dl.exe',
|
||||
'tar': 'youtube-dl-%s.tar.gz' % version}
|
||||
for key, filename in filenames.items():
|
||||
print('Downloading and checksumming %s...' %filename)
|
||||
url = 'http://youtube-dl.org/downloads/%s/%s' % (version, filename)
|
||||
data = urllib.request.urlopen(url).read()
|
||||
sha256sum = hashlib.sha256(data).hexdigest()
|
||||
new_version[key] = (url, sha256sum)
|
||||
print('Downloading and checksumming %s...' % filename)
|
||||
url = 'https://yt-dl.org/downloads/%s/%s' % (version, filename)
|
||||
data = urllib.request.urlopen(url).read()
|
||||
sha256sum = hashlib.sha256(data).hexdigest()
|
||||
new_version[key] = (url, sha256sum)
|
||||
|
||||
versions_info['versions'][version] = new_version
|
||||
versions_info['latest'] = version
|
||||
|
||||
json.dump(versions_info, open('update/versions.json', 'w'), indent=4, sort_keys=True)
|
||||
with open('update/versions.json', 'w') as jsonf:
|
||||
json.dump(versions_info, jsonf, indent=4, sort_keys=True)
|
||||
|
||||
@ -22,7 +22,7 @@ entry_template=textwrap.dedent("""
|
||||
<atom:link href="http://rg3.github.io/youtube-dl" />
|
||||
<atom:content type="xhtml">
|
||||
<div xmlns="http://www.w3.org/1999/xhtml">
|
||||
Downloads available at <a href="http://youtube-dl.org/downloads/@VERSION@/">http://youtube-dl.org/downloads/@VERSION@/</a>
|
||||
Downloads available at <a href="https://yt-dl.org/downloads/@VERSION@/">https://yt-dl.org/downloads/@VERSION@/</a>
|
||||
</div>
|
||||
</atom:content>
|
||||
<atom:author>
|
||||
@ -54,4 +54,3 @@ atom_template = atom_template.replace('@ENTRIES@', entries_str)
|
||||
with open('update/releases.atom','w',encoding='utf-8') as atom_file:
|
||||
atom_file.write(atom_template)
|
||||
|
||||
|
||||
|
||||
@ -67,7 +67,7 @@ RELEASE_FILES="youtube-dl youtube-dl.exe youtube-dl-$version.tar.gz"
|
||||
(cd build/$version/ && sha512sum $RELEASE_FILES > SHA2-512SUMS)
|
||||
git checkout HEAD -- youtube-dl youtube-dl.exe
|
||||
|
||||
/bin/echo -e "\n### Signing and uploading the new binaries to youtube-dl.org..."
|
||||
/bin/echo -e "\n### Signing and uploading the new binaries to yt-dl.org ..."
|
||||
for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
|
||||
scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
|
||||
ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
|
||||
|
||||
@ -11,30 +11,36 @@ tests = [
|
||||
# 90
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'`",
|
||||
"mrtyuioplkjhgfdsazxcvbne1234567890QWER[YUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={`]}|"),
|
||||
# 88
|
||||
# 89
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<'",
|
||||
"/?;:|}<[{=+-_)(*&^%$#@!MqBVCXZASDFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuyt"),
|
||||
# 88 - vflapUV9V 2013/08/28
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<",
|
||||
"J:|}][{=+-_)(*&;%$#@>MNBVCXZASDFGH^KLPOIUYTREWQ0987654321mnbvcxzasdfghrklpoiuytej"),
|
||||
# 87 - vflART1Nf 2013/07/24
|
||||
"ioplkjhgfdsazxcvbnm12<4567890QWERTYUIOZLKJHGFDSAeXCVBNM!@#$%^&*()_-+={[]}|:;?/>.3"),
|
||||
# 87
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
|
||||
"tyuioplkjhgfdsazxcv<nm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>"),
|
||||
# 86 - vflm_D8eE 2013/07/31
|
||||
"uioplkjhgfdsazxcvbnm1t34567890QWE2TYUIOPLKJHGFDSAZXCVeNM!@#$^&*()_-+={[]}|:;?/>.<"),
|
||||
# 86 - vflg0g8PQ 2013/08/29
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
|
||||
">.1}|[{=+-_)(*&^%$#@!MNBVCXZASDFGHJK<POIUYTREW509876L432/mnbvcxzasdfghjklpoiuytre"),
|
||||
# 85 - vflSAFCP9 2013/07/19
|
||||
">/?;}|[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWq0987654321mnbvcxzasdfghjklpoiuytr"),
|
||||
# 85
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<",
|
||||
"ertyuiqplkjhgfdsazx$vbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#<%^&*()_-+={[};?/c"),
|
||||
# 84
|
||||
".>/?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWQ0q876543r1mnbvcx9asdfghjklpoiuyt2"),
|
||||
# 84 - vflg0g8PQ 2013/08/29 (sporadic)
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
|
||||
"<.>?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWe098765432rmnbvcxzasdfghjklpoiuyt1"),
|
||||
# 83 - vflTWC9KW 2013/08/01
|
||||
">?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWq0987654321mnbvcxzasdfghjklpoiuytr"),
|
||||
# 83
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
|
||||
"qwertyuioplkjhg>dsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/f"),
|
||||
# 82
|
||||
".>/?;}[{=+_)(*&^%<#!MNBVCXZASPFGHJKLwOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytreq"),
|
||||
# 82 - vflZK4ZYR 2013/08/23
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
|
||||
"Q>/?;}[{=+-(*<^%$#@!MNBVCXZASDFGHKLPOIUY8REWT0q&7654321mnbvcxzasdfghjklpoiuytrew9"),
|
||||
"wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>.<"),
|
||||
# 81 - vflLC8JvQ 2013/07/25
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.",
|
||||
"C>/?;}[{=+-(*&^%$#@!MNBVYXZASDFGHKLPOIU.TREWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
|
||||
# 80 - vflZK4ZYR 2013/08/23 (sporadic)
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>",
|
||||
"wertyuioplkjhgfdsaqxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&z(-+={[};?/>"),
|
||||
# 79 - vflLC8JvQ 2013/07/25 (sporadic)
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/",
|
||||
"Z?;}[{=+-(*&^%$#@!MNBVCXRASDFGHKLPOIUYT/EWQ0q87659321mnbvcxzasdfghjkl4oiuytrewp"),
|
||||
|
||||
@ -50,6 +50,7 @@ class TestAllURLsMatching(unittest.TestCase):
|
||||
self.assertEqual(YoutubeIE()._extract_id('http://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
|
||||
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?&v=BaW_jenozKc'), 'BaW_jenozKc')
|
||||
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc'), 'BaW_jenozKc')
|
||||
self.assertEqual(YoutubeIE()._extract_id('https://www.youtube.com/watch_popup?v=BaW_jenozKc'), 'BaW_jenozKc')
|
||||
|
||||
def test_no_duplicates(self):
|
||||
ies = gen_extractors()
|
||||
|
||||
@ -127,12 +127,11 @@ def generator(test_case):
|
||||
info_dict = json.load(infof)
|
||||
for (info_field, expected) in tc.get('info_dict', {}).items():
|
||||
if isinstance(expected, compat_str) and expected.startswith('md5:'):
|
||||
self.assertEqual(expected, 'md5:' + md5(info_dict.get(info_field)))
|
||||
got = 'md5:' + md5(info_dict.get(info_field))
|
||||
else:
|
||||
got = info_dict.get(info_field)
|
||||
self.assertEqual(
|
||||
expected, got,
|
||||
u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
|
||||
self.assertEqual(expected, got,
|
||||
u'invalid value for field %s, expected %r, got %r' % (info_field, expected, got))
|
||||
|
||||
# If checkable fields are missing from the test case, print the info_dict
|
||||
test_info_dict = dict((key, value if not isinstance(value, compat_str) or len(value) < 250 else 'md5:' + md5(value))
|
||||
|
||||
@ -35,47 +35,47 @@ class TestYoutubeSubtitles(unittest.TestCase):
|
||||
DL.params['writesubtitles'] = True
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('QRS8MkLhQmM')
|
||||
sub = info_dict[0]['subtitles'][0]
|
||||
self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
|
||||
sub = info_dict[0]['subtitles']['en']
|
||||
self.assertEqual(md5(sub), '4cd9278a35ba2305f47354ee13472260')
|
||||
def test_youtube_subtitles_it(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['writesubtitles'] = True
|
||||
DL.params['subtitleslang'] = 'it'
|
||||
DL.params['subtitleslangs'] = ['it']
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('QRS8MkLhQmM')
|
||||
sub = info_dict[0]['subtitles'][0]
|
||||
self.assertEqual(md5(sub[2]), '164a51f16f260476a05b50fe4c2f161d')
|
||||
sub = info_dict[0]['subtitles']['it']
|
||||
self.assertEqual(md5(sub), '164a51f16f260476a05b50fe4c2f161d')
|
||||
def test_youtube_onlysubtitles(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['writesubtitles'] = True
|
||||
DL.params['onlysubtitles'] = True
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('QRS8MkLhQmM')
|
||||
sub = info_dict[0]['subtitles'][0]
|
||||
self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
|
||||
sub = info_dict[0]['subtitles']['en']
|
||||
self.assertEqual(md5(sub), '4cd9278a35ba2305f47354ee13472260')
|
||||
def test_youtube_allsubtitles(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['allsubtitles'] = True
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('QRS8MkLhQmM')
|
||||
subtitles = info_dict[0]['subtitles']
|
||||
self.assertEqual(len(subtitles), 13)
|
||||
self.assertEqual(len(subtitles.keys()), 13)
|
||||
def test_youtube_subtitles_sbv_format(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['writesubtitles'] = True
|
||||
DL.params['subtitlesformat'] = 'sbv'
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('QRS8MkLhQmM')
|
||||
sub = info_dict[0]['subtitles'][0]
|
||||
self.assertEqual(md5(sub[2]), '13aeaa0c245a8bed9a451cb643e3ad8b')
|
||||
sub = info_dict[0]['subtitles']['en']
|
||||
self.assertEqual(md5(sub), '13aeaa0c245a8bed9a451cb643e3ad8b')
|
||||
def test_youtube_subtitles_vtt_format(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['writesubtitles'] = True
|
||||
DL.params['subtitlesformat'] = 'vtt'
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('QRS8MkLhQmM')
|
||||
sub = info_dict[0]['subtitles'][0]
|
||||
self.assertEqual(md5(sub[2]), '356cdc577fde0c6783b9b822e7206ff7')
|
||||
sub = info_dict[0]['subtitles']['en']
|
||||
self.assertEqual(md5(sub), '356cdc577fde0c6783b9b822e7206ff7')
|
||||
def test_youtube_list_subtitles(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['listsubtitles'] = True
|
||||
@ -85,11 +85,20 @@ class TestYoutubeSubtitles(unittest.TestCase):
|
||||
def test_youtube_automatic_captions(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['writeautomaticsub'] = True
|
||||
DL.params['subtitleslang'] = 'it'
|
||||
DL.params['subtitleslangs'] = ['it']
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('8YoUxe5ncPo')
|
||||
sub = info_dict[0]['subtitles'][0]
|
||||
self.assertTrue(sub[2] is not None)
|
||||
sub = info_dict[0]['subtitles']['it']
|
||||
self.assertTrue(sub is not None)
|
||||
def test_youtube_multiple_langs(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['writesubtitles'] = True
|
||||
langs = ['it', 'fr', 'de']
|
||||
DL.params['subtitleslangs'] = langs
|
||||
IE = YoutubeIE(DL)
|
||||
subtitles = IE.extract('QRS8MkLhQmM')[0]['subtitles']
|
||||
for lang in langs:
|
||||
self.assertTrue(subtitles.get(lang) is not None, u'Subtitles for \'%s\' not extracted' % lang)
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
@ -63,6 +63,17 @@ class FileDownloader(object):
|
||||
converted = float(bytes) / float(1024 ** exponent)
|
||||
return '%.2f%s' % (converted, suffix)
|
||||
|
||||
@staticmethod
|
||||
def format_seconds(seconds):
|
||||
(mins, secs) = divmod(seconds, 60)
|
||||
(hours, eta_mins) = divmod(mins, 60)
|
||||
if hours > 99:
|
||||
return '--:--:--'
|
||||
if hours == 0:
|
||||
return '%02d:%02d' % (mins, secs)
|
||||
else:
|
||||
return '%02d:%02d:%02d' % (hours, mins, secs)
|
||||
|
||||
@staticmethod
|
||||
def calc_percent(byte_counter, data_len):
|
||||
if data_len is None:
|
||||
@ -78,10 +89,7 @@ class FileDownloader(object):
|
||||
return '--:--'
|
||||
rate = float(current) / dif
|
||||
eta = int((float(total) - float(current)) / rate)
|
||||
(eta_mins, eta_secs) = divmod(eta, 60)
|
||||
if eta_mins > 99:
|
||||
return '--:--'
|
||||
return '%02d:%02d' % (eta_mins, eta_secs)
|
||||
return FileDownloader.format_seconds(eta)
|
||||
|
||||
@staticmethod
|
||||
def calc_speed(start, now, bytes):
|
||||
@ -230,12 +238,14 @@ class FileDownloader(object):
|
||||
"""Report it was impossible to resume download."""
|
||||
self.to_screen(u'[download] Unable to resume')
|
||||
|
||||
def report_finish(self):
|
||||
def report_finish(self, data_len_str, tot_time):
|
||||
"""Report download finished."""
|
||||
if self.params.get('noprogress', False):
|
||||
self.to_screen(u'[download] Download completed')
|
||||
else:
|
||||
self.to_screen(u'')
|
||||
clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
|
||||
self.to_screen(u'\r%s[download] 100%% of %s in %s' %
|
||||
(clear_line, data_len_str, self.format_seconds(tot_time)))
|
||||
|
||||
def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
|
||||
self.report_destination(filename)
|
||||
@ -597,7 +607,7 @@ class FileDownloader(object):
|
||||
self.report_error(u'Did not get any data blocks')
|
||||
return False
|
||||
stream.close()
|
||||
self.report_finish()
|
||||
self.report_finish(data_len_str, (time.time() - start))
|
||||
if data_len is not None and byte_counter != data_len:
|
||||
raise ContentTooShortError(byte_counter, int(data_len))
|
||||
self.try_rename(tmpfilename, filename)
|
||||
|
||||
@ -71,12 +71,17 @@ class FFmpegPostProcessor(PostProcessor):
|
||||
programs = ['avprobe', 'avconv', 'ffmpeg', 'ffprobe']
|
||||
return dict((program, executable(program)) for program in programs)
|
||||
|
||||
def run_ffmpeg(self, path, out_path, opts):
|
||||
def run_ffmpeg_multiple_files(self, input_paths, out_path, opts):
|
||||
if not self._exes['ffmpeg'] and not self._exes['avconv']:
|
||||
raise FFmpegPostProcessorError(u'ffmpeg or avconv not found. Please install one.')
|
||||
cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y', '-i', encodeFilename(path)]
|
||||
|
||||
files_cmd = []
|
||||
for path in input_paths:
|
||||
files_cmd.extend(['-i', encodeFilename(path)])
|
||||
cmd = ([self._exes['avconv'] or self._exes['ffmpeg'], '-y'] + files_cmd
|
||||
+ opts +
|
||||
[encodeFilename(self._ffmpeg_filename_argument(out_path))])
|
||||
|
||||
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
|
||||
stdout,stderr = p.communicate()
|
||||
if p.returncode != 0:
|
||||
@ -84,6 +89,9 @@ class FFmpegPostProcessor(PostProcessor):
|
||||
msg = stderr.strip().split('\n')[-1]
|
||||
raise FFmpegPostProcessorError(msg)
|
||||
|
||||
def run_ffmpeg(self, path, out_path, opts):
|
||||
self.run_ffmpeg_multiple_files([path], out_path, opts)
|
||||
|
||||
def _ffmpeg_filename_argument(self, fn):
|
||||
# ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
|
||||
if fn.startswith(u'-'):
|
||||
@ -129,7 +137,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
|
||||
try:
|
||||
FFmpegPostProcessor.run_ffmpeg(self, path, out_path, opts)
|
||||
except FFmpegPostProcessorError as err:
|
||||
raise AudioConversionError(err.message)
|
||||
raise AudioConversionError(err.msg)
|
||||
|
||||
def run(self, information):
|
||||
path = information['filepath']
|
||||
@ -199,7 +207,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
|
||||
except:
|
||||
etype,e,tb = sys.exc_info()
|
||||
if isinstance(e, AudioConversionError):
|
||||
msg = u'audio conversion failed: ' + e.message
|
||||
msg = u'audio conversion failed: ' + e.msg
|
||||
else:
|
||||
msg = u'error running ' + (self._exes['avconv'] and 'avconv' or 'ffmpeg')
|
||||
raise PostProcessingError(msg)
|
||||
@ -232,3 +240,227 @@ class FFmpegVideoConvertor(FFmpegPostProcessor):
|
||||
information['format'] = self._preferedformat
|
||||
information['ext'] = self._preferedformat
|
||||
return False,information
|
||||
|
||||
|
||||
class FFmpegEmbedSubtitlePP(FFmpegPostProcessor):
|
||||
# See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
|
||||
_lang_map = {
|
||||
'aa': 'aar',
|
||||
'ab': 'abk',
|
||||
'ae': 'ave',
|
||||
'af': 'afr',
|
||||
'ak': 'aka',
|
||||
'am': 'amh',
|
||||
'an': 'arg',
|
||||
'ar': 'ara',
|
||||
'as': 'asm',
|
||||
'av': 'ava',
|
||||
'ay': 'aym',
|
||||
'az': 'aze',
|
||||
'ba': 'bak',
|
||||
'be': 'bel',
|
||||
'bg': 'bul',
|
||||
'bh': 'bih',
|
||||
'bi': 'bis',
|
||||
'bm': 'bam',
|
||||
'bn': 'ben',
|
||||
'bo': 'bod',
|
||||
'br': 'bre',
|
||||
'bs': 'bos',
|
||||
'ca': 'cat',
|
||||
'ce': 'che',
|
||||
'ch': 'cha',
|
||||
'co': 'cos',
|
||||
'cr': 'cre',
|
||||
'cs': 'ces',
|
||||
'cu': 'chu',
|
||||
'cv': 'chv',
|
||||
'cy': 'cym',
|
||||
'da': 'dan',
|
||||
'de': 'deu',
|
||||
'dv': 'div',
|
||||
'dz': 'dzo',
|
||||
'ee': 'ewe',
|
||||
'el': 'ell',
|
||||
'en': 'eng',
|
||||
'eo': 'epo',
|
||||
'es': 'spa',
|
||||
'et': 'est',
|
||||
'eu': 'eus',
|
||||
'fa': 'fas',
|
||||
'ff': 'ful',
|
||||
'fi': 'fin',
|
||||
'fj': 'fij',
|
||||
'fo': 'fao',
|
||||
'fr': 'fra',
|
||||
'fy': 'fry',
|
||||
'ga': 'gle',
|
||||
'gd': 'gla',
|
||||
'gl': 'glg',
|
||||
'gn': 'grn',
|
||||
'gu': 'guj',
|
||||
'gv': 'glv',
|
||||
'ha': 'hau',
|
||||
'he': 'heb',
|
||||
'hi': 'hin',
|
||||
'ho': 'hmo',
|
||||
'hr': 'hrv',
|
||||
'ht': 'hat',
|
||||
'hu': 'hun',
|
||||
'hy': 'hye',
|
||||
'hz': 'her',
|
||||
'ia': 'ina',
|
||||
'id': 'ind',
|
||||
'ie': 'ile',
|
||||
'ig': 'ibo',
|
||||
'ii': 'iii',
|
||||
'ik': 'ipk',
|
||||
'io': 'ido',
|
||||
'is': 'isl',
|
||||
'it': 'ita',
|
||||
'iu': 'iku',
|
||||
'ja': 'jpn',
|
||||
'jv': 'jav',
|
||||
'ka': 'kat',
|
||||
'kg': 'kon',
|
||||
'ki': 'kik',
|
||||
'kj': 'kua',
|
||||
'kk': 'kaz',
|
||||
'kl': 'kal',
|
||||
'km': 'khm',
|
||||
'kn': 'kan',
|
||||
'ko': 'kor',
|
||||
'kr': 'kau',
|
||||
'ks': 'kas',
|
||||
'ku': 'kur',
|
||||
'kv': 'kom',
|
||||
'kw': 'cor',
|
||||
'ky': 'kir',
|
||||
'la': 'lat',
|
||||
'lb': 'ltz',
|
||||
'lg': 'lug',
|
||||
'li': 'lim',
|
||||
'ln': 'lin',
|
||||
'lo': 'lao',
|
||||
'lt': 'lit',
|
||||
'lu': 'lub',
|
||||
'lv': 'lav',
|
||||
'mg': 'mlg',
|
||||
'mh': 'mah',
|
||||
'mi': 'mri',
|
||||
'mk': 'mkd',
|
||||
'ml': 'mal',
|
||||
'mn': 'mon',
|
||||
'mr': 'mar',
|
||||
'ms': 'msa',
|
||||
'mt': 'mlt',
|
||||
'my': 'mya',
|
||||
'na': 'nau',
|
||||
'nb': 'nob',
|
||||
'nd': 'nde',
|
||||
'ne': 'nep',
|
||||
'ng': 'ndo',
|
||||
'nl': 'nld',
|
||||
'nn': 'nno',
|
||||
'no': 'nor',
|
||||
'nr': 'nbl',
|
||||
'nv': 'nav',
|
||||
'ny': 'nya',
|
||||
'oc': 'oci',
|
||||
'oj': 'oji',
|
||||
'om': 'orm',
|
||||
'or': 'ori',
|
||||
'os': 'oss',
|
||||
'pa': 'pan',
|
||||
'pi': 'pli',
|
||||
'pl': 'pol',
|
||||
'ps': 'pus',
|
||||
'pt': 'por',
|
||||
'qu': 'que',
|
||||
'rm': 'roh',
|
||||
'rn': 'run',
|
||||
'ro': 'ron',
|
||||
'ru': 'rus',
|
||||
'rw': 'kin',
|
||||
'sa': 'san',
|
||||
'sc': 'srd',
|
||||
'sd': 'snd',
|
||||
'se': 'sme',
|
||||
'sg': 'sag',
|
||||
'si': 'sin',
|
||||
'sk': 'slk',
|
||||
'sl': 'slv',
|
||||
'sm': 'smo',
|
||||
'sn': 'sna',
|
||||
'so': 'som',
|
||||
'sq': 'sqi',
|
||||
'sr': 'srp',
|
||||
'ss': 'ssw',
|
||||
'st': 'sot',
|
||||
'su': 'sun',
|
||||
'sv': 'swe',
|
||||
'sw': 'swa',
|
||||
'ta': 'tam',
|
||||
'te': 'tel',
|
||||
'tg': 'tgk',
|
||||
'th': 'tha',
|
||||
'ti': 'tir',
|
||||
'tk': 'tuk',
|
||||
'tl': 'tgl',
|
||||
'tn': 'tsn',
|
||||
'to': 'ton',
|
||||
'tr': 'tur',
|
||||
'ts': 'tso',
|
||||
'tt': 'tat',
|
||||
'tw': 'twi',
|
||||
'ty': 'tah',
|
||||
'ug': 'uig',
|
||||
'uk': 'ukr',
|
||||
'ur': 'urd',
|
||||
'uz': 'uzb',
|
||||
've': 'ven',
|
||||
'vi': 'vie',
|
||||
'vo': 'vol',
|
||||
'wa': 'wln',
|
||||
'wo': 'wol',
|
||||
'xh': 'xho',
|
||||
'yi': 'yid',
|
||||
'yo': 'yor',
|
||||
'za': 'zha',
|
||||
'zh': 'zho',
|
||||
'zu': 'zul',
|
||||
}
|
||||
|
||||
def __init__(self, downloader=None, subtitlesformat='srt'):
|
||||
super(FFmpegEmbedSubtitlePP, self).__init__(downloader)
|
||||
self._subformat = subtitlesformat
|
||||
|
||||
@classmethod
|
||||
def _conver_lang_code(cls, code):
|
||||
"""Convert language code from ISO 639-1 to ISO 639-2/T"""
|
||||
return cls._lang_map.get(code[:2])
|
||||
|
||||
def run(self, information):
|
||||
if information['ext'] != u'mp4':
|
||||
self._downloader.to_screen(u'[ffmpeg] Subtitles can only be embedded in mp4 files')
|
||||
return True, information
|
||||
sub_langs = [key for key in information['subtitles']]
|
||||
|
||||
filename = information['filepath']
|
||||
input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs]
|
||||
|
||||
opts = ['-map', '0:0', '-map', '0:1', '-c:v', 'copy', '-c:a', 'copy']
|
||||
for (i, lang) in enumerate(sub_langs):
|
||||
opts.extend(['-map', '%d:0' % (i+1), '-c:s:%d' % i, 'mov_text'])
|
||||
lang_code = self._conver_lang_code(lang)
|
||||
if lang_code is not None:
|
||||
opts.extend(['-metadata:s:s:%d' % i, 'language=%s' % lang_code])
|
||||
opts.extend(['-f', 'mp4'])
|
||||
|
||||
temp_filename = filename + u'.temp'
|
||||
self._downloader.to_screen(u'[ffmpeg] Embedding subtitles in \'%s\'' % filename)
|
||||
self.run_ffmpeg_multiple_files(input_files, temp_filename, opts)
|
||||
os.remove(encodeFilename(filename))
|
||||
os.rename(encodeFilename(temp_filename), encodeFilename(filename))
|
||||
|
||||
return True, information
|
||||
|
||||
@ -76,7 +76,7 @@ class YoutubeDL(object):
|
||||
allsubtitles: Downloads all the subtitles of the video
|
||||
listsubtitles: Lists all available subtitles for the video
|
||||
subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt)
|
||||
subtitleslang: Language of the subtitles to download
|
||||
subtitleslangs: List of languages of the subtitles to download
|
||||
keepvideo: Keep the video file after post-processing
|
||||
daterange: A DateRange object, download only if the upload_date is in the range.
|
||||
skip_download: Skip the actual download of the video file
|
||||
@ -97,6 +97,7 @@ class YoutubeDL(object):
|
||||
def __init__(self, params):
|
||||
"""Create a FileDownloader object with the given options."""
|
||||
self._ies = []
|
||||
self._ies_instances = {}
|
||||
self._pps = []
|
||||
self._progress_hooks = []
|
||||
self._download_retcode = 0
|
||||
@ -111,8 +112,21 @@ class YoutubeDL(object):
|
||||
def add_info_extractor(self, ie):
|
||||
"""Add an InfoExtractor object to the end of the list."""
|
||||
self._ies.append(ie)
|
||||
self._ies_instances[ie.ie_key()] = ie
|
||||
ie.set_downloader(self)
|
||||
|
||||
def get_info_extractor(self, ie_key):
|
||||
"""
|
||||
Get an instance of an IE with name ie_key, it will try to get one from
|
||||
the _ies list, if there's no instance it will create a new one and add
|
||||
it to the extractor list.
|
||||
"""
|
||||
ie = self._ies_instances.get(ie_key)
|
||||
if ie is None:
|
||||
ie = get_info_extractor(ie_key)()
|
||||
self.add_info_extractor(ie)
|
||||
return ie
|
||||
|
||||
def add_default_info_extractors(self):
|
||||
"""
|
||||
Add the InfoExtractors returned by gen_extractors to the end of the list
|
||||
@ -294,9 +308,7 @@ class YoutubeDL(object):
|
||||
'''
|
||||
|
||||
if ie_key:
|
||||
ie = get_info_extractor(ie_key)()
|
||||
ie.set_downloader(self)
|
||||
ies = [ie]
|
||||
ies = [self.get_info_extractor(ie_key)]
|
||||
else:
|
||||
ies = self._ies
|
||||
|
||||
@ -448,7 +460,8 @@ class YoutubeDL(object):
|
||||
if self.params.get('forceid', False):
|
||||
compat_print(info_dict['id'])
|
||||
if self.params.get('forceurl', False):
|
||||
compat_print(info_dict['url'])
|
||||
# For RTMP URLs, also include the playpath
|
||||
compat_print(info_dict['url'] + info_dict.get('play_path', u''))
|
||||
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
|
||||
compat_print(info_dict['thumbnail'])
|
||||
if self.params.get('forcedescription', False) and 'description' in info_dict:
|
||||
@ -483,41 +496,28 @@ class YoutubeDL(object):
|
||||
self.report_error(u'Cannot write description file ' + descfn)
|
||||
return
|
||||
|
||||
if (self.params.get('writesubtitles', False) or self.params.get('writeautomaticsub')) and 'subtitles' in info_dict and info_dict['subtitles']:
|
||||
subtitles_are_requested = any([self.params.get('writesubtitles', False),
|
||||
self.params.get('writeautomaticsub'),
|
||||
self.params.get('allsubtitles', False)])
|
||||
|
||||
if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']:
|
||||
# subtitles download errors are already managed as troubles in relevant IE
|
||||
# that way it will silently go on when used with unsupporting IE
|
||||
subtitle = info_dict['subtitles'][0]
|
||||
(sub_error, sub_lang, sub) = subtitle
|
||||
subtitles = info_dict['subtitles']
|
||||
sub_format = self.params.get('subtitlesformat')
|
||||
if sub_error:
|
||||
self.report_warning("Some error while getting the subtitles")
|
||||
else:
|
||||
for sub_lang in subtitles.keys():
|
||||
sub = subtitles[sub_lang]
|
||||
if sub is None:
|
||||
continue
|
||||
try:
|
||||
sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
|
||||
sub_filename = subtitles_filename(filename, sub_lang, sub_format)
|
||||
self.report_writesubtitles(sub_filename)
|
||||
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
|
||||
subfile.write(sub)
|
||||
subfile.write(sub)
|
||||
except (OSError, IOError):
|
||||
self.report_error(u'Cannot write subtitles file ' + descfn)
|
||||
return
|
||||
|
||||
if self.params.get('allsubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
|
||||
subtitles = info_dict['subtitles']
|
||||
sub_format = self.params.get('subtitlesformat')
|
||||
for subtitle in subtitles:
|
||||
(sub_error, sub_lang, sub) = subtitle
|
||||
if sub_error:
|
||||
self.report_warning("Some error while getting the subtitles")
|
||||
else:
|
||||
try:
|
||||
sub_filename = filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
|
||||
self.report_writesubtitles(sub_filename)
|
||||
with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile:
|
||||
subfile.write(sub)
|
||||
except (OSError, IOError):
|
||||
self.report_error(u'Cannot write subtitles file ' + descfn)
|
||||
return
|
||||
|
||||
if self.params.get('writeinfojson', False):
|
||||
infofn = filename + u'.info.json'
|
||||
self.report_writeinfojson(infofn)
|
||||
|
||||
@ -27,6 +27,7 @@ __authors__ = (
|
||||
'Johny Mo Swag',
|
||||
'Axel Noack',
|
||||
'Albert Kim',
|
||||
'Pierre Rudloff',
|
||||
)
|
||||
|
||||
__license__ = 'Public Domain'
|
||||
@ -44,6 +45,7 @@ import sys
|
||||
import warnings
|
||||
import platform
|
||||
|
||||
|
||||
from .utils import *
|
||||
from .update import update_self
|
||||
from .version import __version__
|
||||
@ -82,6 +84,9 @@ def parseOpts(overrideArguments=None):
|
||||
|
||||
return "".join(opts)
|
||||
|
||||
def _comma_separated_values_options_callback(option, opt_str, value, parser):
|
||||
setattr(parser.values, option.dest, value.split(','))
|
||||
|
||||
def _find_term_columns():
|
||||
columns = os.environ.get('COLUMNS', None)
|
||||
if columns:
|
||||
@ -95,6 +100,16 @@ def parseOpts(overrideArguments=None):
|
||||
pass
|
||||
return None
|
||||
|
||||
def _hide_login_info(opts):
|
||||
opts = list(opts)
|
||||
for private_opt in ['-p', '--password', '-u', '--username']:
|
||||
try:
|
||||
i = opts.index(private_opt)
|
||||
opts[i+1] = '<PRIVATE>'
|
||||
except ValueError:
|
||||
pass
|
||||
return opts
|
||||
|
||||
max_width = 80
|
||||
max_help_position = 80
|
||||
|
||||
@ -119,6 +134,7 @@ def parseOpts(overrideArguments=None):
|
||||
selection = optparse.OptionGroup(parser, 'Video Selection')
|
||||
authentication = optparse.OptionGroup(parser, 'Authentication Options')
|
||||
video_format = optparse.OptionGroup(parser, 'Video Format Options')
|
||||
subtitles = optparse.OptionGroup(parser, 'Subtitle Options')
|
||||
downloader = optparse.OptionGroup(parser, 'Download Options')
|
||||
postproc = optparse.OptionGroup(parser, 'Post-processing Options')
|
||||
filesystem = optparse.OptionGroup(parser, 'Filesystem Options')
|
||||
@ -185,27 +201,29 @@ def parseOpts(overrideArguments=None):
|
||||
action='store', dest='format_limit', metavar='FORMAT', help='highest quality format to download')
|
||||
video_format.add_option('-F', '--list-formats',
|
||||
action='store_true', dest='listformats', help='list all available formats (currently youtube only)')
|
||||
video_format.add_option('--write-sub', '--write-srt',
|
||||
|
||||
subtitles.add_option('--write-sub', '--write-srt',
|
||||
action='store_true', dest='writesubtitles',
|
||||
help='write subtitle file (currently youtube only)', default=False)
|
||||
video_format.add_option('--write-auto-sub', '--write-automatic-sub',
|
||||
subtitles.add_option('--write-auto-sub', '--write-automatic-sub',
|
||||
action='store_true', dest='writeautomaticsub',
|
||||
help='write automatic subtitle file (currently youtube only)', default=False)
|
||||
video_format.add_option('--only-sub',
|
||||
subtitles.add_option('--only-sub',
|
||||
action='store_true', dest='skip_download',
|
||||
help='[deprecated] alias of --skip-download', default=False)
|
||||
video_format.add_option('--all-subs',
|
||||
subtitles.add_option('--all-subs',
|
||||
action='store_true', dest='allsubtitles',
|
||||
help='downloads all the available subtitles of the video (currently youtube only)', default=False)
|
||||
video_format.add_option('--list-subs',
|
||||
help='downloads all the available subtitles of the video', default=False)
|
||||
subtitles.add_option('--list-subs',
|
||||
action='store_true', dest='listsubtitles',
|
||||
help='lists all available subtitles for the video (currently youtube only)', default=False)
|
||||
video_format.add_option('--sub-format',
|
||||
help='lists all available subtitles for the video', default=False)
|
||||
subtitles.add_option('--sub-format',
|
||||
action='store', dest='subtitlesformat', metavar='FORMAT',
|
||||
help='subtitle format [srt/sbv/vtt] (default=srt) (currently youtube only)', default='srt')
|
||||
video_format.add_option('--sub-lang', '--srt-lang',
|
||||
action='store', dest='subtitleslang', metavar='LANG',
|
||||
help='language of the subtitles to download (optional) use IETF language tags like \'en\'')
|
||||
help='subtitle format (default=srt) ([sbv/vtt] youtube only)', default='srt')
|
||||
subtitles.add_option('--sub-lang', '--sub-langs', '--srt-lang',
|
||||
action='callback', dest='subtitleslang', metavar='LANGS', type='str',
|
||||
default=[], callback=_comma_separated_values_options_callback,
|
||||
help='languages of the subtitles to download (optional) separated by commas, use IETF language tags like \'en,pt\'')
|
||||
|
||||
downloader.add_option('-r', '--rate-limit',
|
||||
dest='ratelimit', metavar='LIMIT', help='maximum download rate (e.g. 50k or 44.6m)')
|
||||
@ -320,6 +338,8 @@ def parseOpts(overrideArguments=None):
|
||||
help='keeps the video file on disk after the post-processing; the video is erased by default')
|
||||
postproc.add_option('--no-post-overwrites', action='store_true', dest='nopostoverwrites', default=False,
|
||||
help='do not overwrite post-processed files; the post-processed files are overwritten by default')
|
||||
postproc.add_option('--embed-subs', action='store_true', dest='embedsubtitles', default=False,
|
||||
help='embed subtitles in the video (only for mp4 videos)')
|
||||
|
||||
|
||||
parser.add_option_group(general)
|
||||
@ -328,6 +348,7 @@ def parseOpts(overrideArguments=None):
|
||||
parser.add_option_group(filesystem)
|
||||
parser.add_option_group(verbosity)
|
||||
parser.add_option_group(video_format)
|
||||
parser.add_option_group(subtitles)
|
||||
parser.add_option_group(authentication)
|
||||
parser.add_option_group(postproc)
|
||||
|
||||
@ -343,13 +364,13 @@ def parseOpts(overrideArguments=None):
|
||||
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
|
||||
systemConf = _readOptions('/etc/youtube-dl.conf')
|
||||
userConf = _readOptions(userConfFile)
|
||||
commandLineConf = sys.argv[1:]
|
||||
commandLineConf = sys.argv[1:]
|
||||
argv = systemConf + userConf + commandLineConf
|
||||
opts, args = parser.parse_args(argv)
|
||||
if opts.verbose:
|
||||
sys.stderr.write(u'[debug] System config: ' + repr(systemConf) + '\n')
|
||||
sys.stderr.write(u'[debug] User config: ' + repr(userConf) + '\n')
|
||||
sys.stderr.write(u'[debug] Command-line args: ' + repr(commandLineConf) + '\n')
|
||||
sys.stderr.write(u'[debug] System config: ' + repr(_hide_login_info(systemConf)) + '\n')
|
||||
sys.stderr.write(u'[debug] User config: ' + repr(_hide_login_info(userConf)) + '\n')
|
||||
sys.stderr.write(u'[debug] Command-line args: ' + repr(_hide_login_info(commandLineConf)) + '\n')
|
||||
|
||||
return parser, opts, args
|
||||
|
||||
@ -381,7 +402,7 @@ def _real_main(argv=None):
|
||||
# Set user agent
|
||||
if opts.user_agent is not None:
|
||||
std_headers['User-Agent'] = opts.user_agent
|
||||
|
||||
|
||||
# Set referer
|
||||
if opts.referer is not None:
|
||||
std_headers['Referer'] = opts.referer
|
||||
@ -424,6 +445,10 @@ def _real_main(argv=None):
|
||||
proxy_handler = compat_urllib_request.ProxyHandler(proxies)
|
||||
https_handler = make_HTTPS_handler(opts)
|
||||
opener = compat_urllib_request.build_opener(https_handler, proxy_handler, cookie_processor, YoutubeDLHandler())
|
||||
# Delete the default user-agent header, which would otherwise apply in
|
||||
# cases where our custom HTTP handler doesn't come into play
|
||||
# (See https://github.com/rg3/youtube-dl/issues/1309 for details)
|
||||
opener.addheaders =[]
|
||||
compat_urllib_request.install_opener(opener)
|
||||
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
|
||||
|
||||
@ -571,7 +596,7 @@ def _real_main(argv=None):
|
||||
'allsubtitles': opts.allsubtitles,
|
||||
'listsubtitles': opts.listsubtitles,
|
||||
'subtitlesformat': opts.subtitlesformat,
|
||||
'subtitleslang': opts.subtitleslang,
|
||||
'subtitleslangs': opts.subtitleslang,
|
||||
'matchtitle': decodeOption(opts.matchtitle),
|
||||
'rejecttitle': decodeOption(opts.rejecttitle),
|
||||
'max_downloads': opts.max_downloads,
|
||||
@ -601,7 +626,7 @@ def _real_main(argv=None):
|
||||
sys.exc_clear()
|
||||
except:
|
||||
pass
|
||||
sys.stderr.write(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform()) + u'\n')
|
||||
sys.stderr.write(u'[debug] Python version %s - %s' %(platform.python_version(), platform_name()) + u'\n')
|
||||
sys.stderr.write(u'[debug] Proxy map: ' + str(proxy_handler.proxies) + u'\n')
|
||||
|
||||
ydl.add_default_info_extractors()
|
||||
@ -611,6 +636,8 @@ def _real_main(argv=None):
|
||||
ydl.add_post_processor(FFmpegExtractAudioPP(preferredcodec=opts.audioformat, preferredquality=opts.audioquality, nopostoverwrites=opts.nopostoverwrites))
|
||||
if opts.recodevideo:
|
||||
ydl.add_post_processor(FFmpegVideoConvertor(preferedformat=opts.recodevideo))
|
||||
if opts.embedsubtitles:
|
||||
ydl.add_post_processor(FFmpegEmbedSubtitlePP(subtitlesformat=opts.subtitlesformat))
|
||||
|
||||
# Update version
|
||||
if opts.update_self:
|
||||
|
||||
202
youtube_dl/aes.py
Normal file
202
youtube_dl/aes.py
Normal file
@ -0,0 +1,202 @@
|
||||
__all__ = ['aes_encrypt', 'key_expansion', 'aes_ctr_decrypt', 'aes_decrypt_text']
|
||||
|
||||
import base64
|
||||
from math import ceil
|
||||
|
||||
from .utils import bytes_to_intlist, intlist_to_bytes
|
||||
|
||||
BLOCK_SIZE_BYTES = 16
|
||||
|
||||
def aes_ctr_decrypt(data, key, counter):
|
||||
"""
|
||||
Decrypt with aes in counter mode
|
||||
|
||||
@param {int[]} data cipher
|
||||
@param {int[]} key 16/24/32-Byte cipher key
|
||||
@param {instance} counter Instance whose next_value function (@returns {int[]} 16-Byte block)
|
||||
returns the next counter block
|
||||
@returns {int[]} decrypted data
|
||||
"""
|
||||
expanded_key = key_expansion(key)
|
||||
block_count = int(ceil(float(len(data)) / BLOCK_SIZE_BYTES))
|
||||
|
||||
decrypted_data=[]
|
||||
for i in range(block_count):
|
||||
counter_block = counter.next_value()
|
||||
block = data[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES]
|
||||
block += [0]*(BLOCK_SIZE_BYTES - len(block))
|
||||
|
||||
cipher_counter_block = aes_encrypt(counter_block, expanded_key)
|
||||
decrypted_data += xor(block, cipher_counter_block)
|
||||
decrypted_data = decrypted_data[:len(data)]
|
||||
|
||||
return decrypted_data
|
||||
|
||||
def key_expansion(data):
|
||||
"""
|
||||
Generate key schedule
|
||||
|
||||
@param {int[]} data 16/24/32-Byte cipher key
|
||||
@returns {int[]} 176/208/240-Byte expanded key
|
||||
"""
|
||||
data = data[:] # copy
|
||||
rcon_iteration = 1
|
||||
key_size_bytes = len(data)
|
||||
expanded_key_size_bytes = (key_size_bytes // 4 + 7) * BLOCK_SIZE_BYTES
|
||||
|
||||
while len(data) < expanded_key_size_bytes:
|
||||
temp = data[-4:]
|
||||
temp = key_schedule_core(temp, rcon_iteration)
|
||||
rcon_iteration += 1
|
||||
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
|
||||
|
||||
for _ in range(3):
|
||||
temp = data[-4:]
|
||||
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
|
||||
|
||||
if key_size_bytes == 32:
|
||||
temp = data[-4:]
|
||||
temp = sub_bytes(temp)
|
||||
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
|
||||
|
||||
for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0):
|
||||
temp = data[-4:]
|
||||
data += xor(temp, data[-key_size_bytes : 4-key_size_bytes])
|
||||
data = data[:expanded_key_size_bytes]
|
||||
|
||||
return data
|
||||
|
||||
def aes_encrypt(data, expanded_key):
|
||||
"""
|
||||
Encrypt one block with aes
|
||||
|
||||
@param {int[]} data 16-Byte state
|
||||
@param {int[]} expanded_key 176/208/240-Byte expanded key
|
||||
@returns {int[]} 16-Byte cipher
|
||||
"""
|
||||
rounds = len(expanded_key) // BLOCK_SIZE_BYTES - 1
|
||||
|
||||
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
|
||||
for i in range(1, rounds+1):
|
||||
data = sub_bytes(data)
|
||||
data = shift_rows(data)
|
||||
if i != rounds:
|
||||
data = mix_columns(data)
|
||||
data = xor(data, expanded_key[i*BLOCK_SIZE_BYTES : (i+1)*BLOCK_SIZE_BYTES])
|
||||
|
||||
return data
|
||||
|
||||
def aes_decrypt_text(data, password, key_size_bytes):
|
||||
"""
|
||||
Decrypt text
|
||||
- The first 8 Bytes of decoded 'data' are the 8 high Bytes of the counter
|
||||
- The cipher key is retrieved by encrypting the first 16 Byte of 'password'
|
||||
with the first 'key_size_bytes' Bytes from 'password' (if necessary filled with 0's)
|
||||
- Mode of operation is 'counter'
|
||||
|
||||
@param {str} data Base64 encoded string
|
||||
@param {str,unicode} password Password (will be encoded with utf-8)
|
||||
@param {int} key_size_bytes Possible values: 16 for 128-Bit, 24 for 192-Bit or 32 for 256-Bit
|
||||
@returns {str} Decrypted data
|
||||
"""
|
||||
NONCE_LENGTH_BYTES = 8
|
||||
|
||||
data = bytes_to_intlist(base64.b64decode(data))
|
||||
password = bytes_to_intlist(password.encode('utf-8'))
|
||||
|
||||
key = password[:key_size_bytes] + [0]*(key_size_bytes - len(password))
|
||||
key = aes_encrypt(key[:BLOCK_SIZE_BYTES], key_expansion(key)) * (key_size_bytes // BLOCK_SIZE_BYTES)
|
||||
|
||||
nonce = data[:NONCE_LENGTH_BYTES]
|
||||
cipher = data[NONCE_LENGTH_BYTES:]
|
||||
|
||||
class Counter:
|
||||
__value = nonce + [0]*(BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES)
|
||||
def next_value(self):
|
||||
temp = self.__value
|
||||
self.__value = inc(self.__value)
|
||||
return temp
|
||||
|
||||
decrypted_data = aes_ctr_decrypt(cipher, key, Counter())
|
||||
plaintext = intlist_to_bytes(decrypted_data)
|
||||
|
||||
return plaintext
|
||||
|
||||
RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
|
||||
SBOX = (0x63, 0x7C, 0x77, 0x7B, 0xF2, 0x6B, 0x6F, 0xC5, 0x30, 0x01, 0x67, 0x2B, 0xFE, 0xD7, 0xAB, 0x76,
|
||||
0xCA, 0x82, 0xC9, 0x7D, 0xFA, 0x59, 0x47, 0xF0, 0xAD, 0xD4, 0xA2, 0xAF, 0x9C, 0xA4, 0x72, 0xC0,
|
||||
0xB7, 0xFD, 0x93, 0x26, 0x36, 0x3F, 0xF7, 0xCC, 0x34, 0xA5, 0xE5, 0xF1, 0x71, 0xD8, 0x31, 0x15,
|
||||
0x04, 0xC7, 0x23, 0xC3, 0x18, 0x96, 0x05, 0x9A, 0x07, 0x12, 0x80, 0xE2, 0xEB, 0x27, 0xB2, 0x75,
|
||||
0x09, 0x83, 0x2C, 0x1A, 0x1B, 0x6E, 0x5A, 0xA0, 0x52, 0x3B, 0xD6, 0xB3, 0x29, 0xE3, 0x2F, 0x84,
|
||||
0x53, 0xD1, 0x00, 0xED, 0x20, 0xFC, 0xB1, 0x5B, 0x6A, 0xCB, 0xBE, 0x39, 0x4A, 0x4C, 0x58, 0xCF,
|
||||
0xD0, 0xEF, 0xAA, 0xFB, 0x43, 0x4D, 0x33, 0x85, 0x45, 0xF9, 0x02, 0x7F, 0x50, 0x3C, 0x9F, 0xA8,
|
||||
0x51, 0xA3, 0x40, 0x8F, 0x92, 0x9D, 0x38, 0xF5, 0xBC, 0xB6, 0xDA, 0x21, 0x10, 0xFF, 0xF3, 0xD2,
|
||||
0xCD, 0x0C, 0x13, 0xEC, 0x5F, 0x97, 0x44, 0x17, 0xC4, 0xA7, 0x7E, 0x3D, 0x64, 0x5D, 0x19, 0x73,
|
||||
0x60, 0x81, 0x4F, 0xDC, 0x22, 0x2A, 0x90, 0x88, 0x46, 0xEE, 0xB8, 0x14, 0xDE, 0x5E, 0x0B, 0xDB,
|
||||
0xE0, 0x32, 0x3A, 0x0A, 0x49, 0x06, 0x24, 0x5C, 0xC2, 0xD3, 0xAC, 0x62, 0x91, 0x95, 0xE4, 0x79,
|
||||
0xE7, 0xC8, 0x37, 0x6D, 0x8D, 0xD5, 0x4E, 0xA9, 0x6C, 0x56, 0xF4, 0xEA, 0x65, 0x7A, 0xAE, 0x08,
|
||||
0xBA, 0x78, 0x25, 0x2E, 0x1C, 0xA6, 0xB4, 0xC6, 0xE8, 0xDD, 0x74, 0x1F, 0x4B, 0xBD, 0x8B, 0x8A,
|
||||
0x70, 0x3E, 0xB5, 0x66, 0x48, 0x03, 0xF6, 0x0E, 0x61, 0x35, 0x57, 0xB9, 0x86, 0xC1, 0x1D, 0x9E,
|
||||
0xE1, 0xF8, 0x98, 0x11, 0x69, 0xD9, 0x8E, 0x94, 0x9B, 0x1E, 0x87, 0xE9, 0xCE, 0x55, 0x28, 0xDF,
|
||||
0x8C, 0xA1, 0x89, 0x0D, 0xBF, 0xE6, 0x42, 0x68, 0x41, 0x99, 0x2D, 0x0F, 0xB0, 0x54, 0xBB, 0x16)
|
||||
MIX_COLUMN_MATRIX = ((2,3,1,1),
|
||||
(1,2,3,1),
|
||||
(1,1,2,3),
|
||||
(3,1,1,2))
|
||||
|
||||
def sub_bytes(data):
|
||||
return [SBOX[x] for x in data]
|
||||
|
||||
def rotate(data):
|
||||
return data[1:] + [data[0]]
|
||||
|
||||
def key_schedule_core(data, rcon_iteration):
|
||||
data = rotate(data)
|
||||
data = sub_bytes(data)
|
||||
data[0] = data[0] ^ RCON[rcon_iteration]
|
||||
|
||||
return data
|
||||
|
||||
def xor(data1, data2):
|
||||
return [x^y for x, y in zip(data1, data2)]
|
||||
|
||||
def mix_column(data):
|
||||
data_mixed = []
|
||||
for row in range(4):
|
||||
mixed = 0
|
||||
for column in range(4):
|
||||
addend = data[column]
|
||||
if MIX_COLUMN_MATRIX[row][column] in (2,3):
|
||||
addend <<= 1
|
||||
if addend > 0xff:
|
||||
addend &= 0xff
|
||||
addend ^= 0x1b
|
||||
if MIX_COLUMN_MATRIX[row][column] == 3:
|
||||
addend ^= data[column]
|
||||
mixed ^= addend & 0xff
|
||||
data_mixed.append(mixed)
|
||||
return data_mixed
|
||||
|
||||
def mix_columns(data):
|
||||
data_mixed = []
|
||||
for i in range(4):
|
||||
column = data[i*4 : (i+1)*4]
|
||||
data_mixed += mix_column(column)
|
||||
return data_mixed
|
||||
|
||||
def shift_rows(data):
|
||||
data_shifted = []
|
||||
for column in range(4):
|
||||
for row in range(4):
|
||||
data_shifted.append( data[((column + row) & 0b11) * 4 + row] )
|
||||
return data_shifted
|
||||
|
||||
def inc(data):
|
||||
data = data[:] # copy
|
||||
for i in range(len(data)-1,-1,-1):
|
||||
if data[i] == 255:
|
||||
data[i] = 0
|
||||
else:
|
||||
data[i] = data[i] + 1
|
||||
break
|
||||
return data
|
||||
@ -1,3 +1,5 @@
|
||||
from .appletrailers import AppleTrailersIE
|
||||
from .addanime import AddAnimeIE
|
||||
from .archiveorg import ArchiveOrgIE
|
||||
from .ard import ARDIE
|
||||
from .arte import ArteTvIE
|
||||
@ -6,7 +8,10 @@ from .bandcamp import BandcampIE
|
||||
from .bliptv import BlipTVIE, BlipTVUserIE
|
||||
from .breakcom import BreakIE
|
||||
from .brightcove import BrightcoveIE
|
||||
from .c56 import C56IE
|
||||
from .canalplus import CanalplusIE
|
||||
from .canalc2 import Canalc2IE
|
||||
from .cnn import CNNIE
|
||||
from .collegehumor import CollegeHumorIE
|
||||
from .comedycentral import ComedyCentralIE
|
||||
from .condenast import CondeNastIE
|
||||
@ -29,6 +34,7 @@ from .gametrailers import GametrailersIE
|
||||
from .generic import GenericIE
|
||||
from .googleplus import GooglePlusIE
|
||||
from .googlesearch import GoogleSearchIE
|
||||
from .hark import HarkIE
|
||||
from .hotnewhiphop import HotNewHipHopIE
|
||||
from .howcast import HowcastIE
|
||||
from .hypem import HypemIE
|
||||
@ -36,6 +42,7 @@ from .ign import IGNIE, OneUPIE
|
||||
from .ina import InaIE
|
||||
from .infoq import InfoQIE
|
||||
from .instagram import InstagramIE
|
||||
from .jeuxvideo import JeuxVideoIE
|
||||
from .jukebox import JukeboxIE
|
||||
from .justintv import JustinTVIE
|
||||
from .kankan import KankanIE
|
||||
@ -43,20 +50,28 @@ from .keek import KeekIE
|
||||
from .liveleak import LiveLeakIE
|
||||
from .livestream import LivestreamIE
|
||||
from .metacafe import MetacafeIE
|
||||
from .mit import TechTVMITIE, MITIE
|
||||
from .mixcloud import MixcloudIE
|
||||
from .mtv import MTVIE
|
||||
from .muzu import MuzuTVIE
|
||||
from .myspass import MySpassIE
|
||||
from .myvideo import MyVideoIE
|
||||
from .nba import NBAIE
|
||||
from .nbc import NBCNewsIE
|
||||
from .ooyala import OoyalaIE
|
||||
from .orf import ORFIE
|
||||
from .pbs import PBSIE
|
||||
from .photobucket import PhotobucketIE
|
||||
from .pornotube import PornotubeIE
|
||||
from .rbmaradio import RBMARadioIE
|
||||
from .redtube import RedTubeIE
|
||||
from .ringtv import RingTVIE
|
||||
from .ro220 import Ro220IE
|
||||
from .roxwel import RoxwelIE
|
||||
from .rtlnow import RTLnowIE
|
||||
from .sina import SinaIE
|
||||
from .slashdot import SlashdotIE
|
||||
from .sohu import SohuIE
|
||||
from .soundcloud import SoundcloudIE, SoundcloudSetIE
|
||||
from .spiegel import SpiegelIE
|
||||
from .stanfordoc import StanfordOpenClassroomIE
|
||||
@ -67,9 +82,11 @@ from .ted import TEDIE
|
||||
from .tf1 import TF1IE
|
||||
from .thisav import ThisAVIE
|
||||
from .traileraddict import TrailerAddictIE
|
||||
from .trilulilu import TriluliluIE
|
||||
from .tudou import TudouIE
|
||||
from .tumblr import TumblrIE
|
||||
from .tutv import TutvIE
|
||||
from .unistra import UnistraIE
|
||||
from .ustream import UstreamIE
|
||||
from .vbox7 import Vbox7IE
|
||||
from .veoh import VeohIE
|
||||
@ -77,7 +94,6 @@ from .vevo import VevoIE
|
||||
from .videofyme import VideofyMeIE
|
||||
from .vimeo import VimeoIE, VimeoChannelIE
|
||||
from .vine import VineIE
|
||||
from .c56 import C56IE
|
||||
from .wat import WatIE
|
||||
from .weibo import WeiboIE
|
||||
from .wimp import WimpIE
|
||||
@ -111,12 +127,14 @@ _ALL_CLASSES = [
|
||||
]
|
||||
_ALL_CLASSES.append(GenericIE)
|
||||
|
||||
|
||||
def gen_extractors():
|
||||
""" Return a list of an instance of every supported extractor.
|
||||
The order does matter; the first extractor matched is the one handling the URL.
|
||||
"""
|
||||
return [klass() for klass in _ALL_CLASSES]
|
||||
|
||||
|
||||
def get_info_extractor(ie_name):
|
||||
"""Returns the info extractor class with the given ie_name"""
|
||||
return globals()[ie_name+'IE']
|
||||
|
||||
75
youtube_dl/extractor/addanime.py
Normal file
75
youtube_dl/extractor/addanime.py
Normal file
@ -0,0 +1,75 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_HTTPError,
|
||||
compat_str,
|
||||
compat_urllib_parse,
|
||||
compat_urllib_parse_urlparse,
|
||||
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
|
||||
class AddAnimeIE(InfoExtractor):
|
||||
|
||||
_VALID_URL = r'^http://(?:\w+\.)?add-anime\.net/watch_video.php\?(?:.*?)v=(?P<video_id>[\w_]+)(?:.*)'
|
||||
IE_NAME = u'AddAnime'
|
||||
_TEST = {
|
||||
u'url': u'http://www.add-anime.net/watch_video.php?v=24MR3YO5SAS9',
|
||||
u'file': u'24MR3YO5SAS9.flv',
|
||||
u'md5': u'1036a0e0cd307b95bd8a8c3a5c8cfaf1',
|
||||
u'info_dict': {
|
||||
u"description": u"One Piece 606",
|
||||
u"title": u"One Piece 606"
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
try:
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('video_id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
except ExtractorError as ee:
|
||||
if not isinstance(ee.cause, compat_HTTPError):
|
||||
raise
|
||||
|
||||
redir_webpage = ee.cause.read().decode('utf-8')
|
||||
action = self._search_regex(
|
||||
r'<form id="challenge-form" action="([^"]+)"',
|
||||
redir_webpage, u'Redirect form')
|
||||
vc = self._search_regex(
|
||||
r'<input type="hidden" name="jschl_vc" value="([^"]+)"/>',
|
||||
redir_webpage, u'redirect vc value')
|
||||
av = re.search(
|
||||
r'a\.value = ([0-9]+)[+]([0-9]+)[*]([0-9]+);',
|
||||
redir_webpage)
|
||||
if av is None:
|
||||
raise ExtractorError(u'Cannot find redirect math task')
|
||||
av_res = int(av.group(1)) + int(av.group(2)) * int(av.group(3))
|
||||
|
||||
parsed_url = compat_urllib_parse_urlparse(url)
|
||||
av_val = av_res + len(parsed_url.netloc)
|
||||
confirm_url = (
|
||||
parsed_url.scheme + u'://' + parsed_url.netloc +
|
||||
action + '?' +
|
||||
compat_urllib_parse.urlencode({
|
||||
'jschl_vc': vc, 'jschl_answer': compat_str(av_val)}))
|
||||
self._download_webpage(
|
||||
confirm_url, video_id,
|
||||
note=u'Confirming after redirect')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_url = self._search_regex(r"var normal_video_file = '(.*?)';",
|
||||
webpage, u'video file URL')
|
||||
video_title = self._og_search_title(webpage)
|
||||
video_description = self._og_search_description(webpage)
|
||||
|
||||
return {
|
||||
'_type': 'video',
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': 'flv',
|
||||
'title': video_title,
|
||||
'description': video_description
|
||||
}
|
||||
166
youtube_dl/extractor/appletrailers.py
Normal file
166
youtube_dl/extractor/appletrailers.py
Normal file
@ -0,0 +1,166 @@
|
||||
import re
|
||||
import xml.etree.ElementTree
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
determine_ext,
|
||||
)
|
||||
|
||||
|
||||
class AppleTrailersIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?trailers.apple.com/trailers/(?P<company>[^/]+)/(?P<movie>[^/]+)'
|
||||
_TEST = {
|
||||
u"url": u"http://trailers.apple.com/trailers/wb/manofsteel/",
|
||||
u"playlist": [
|
||||
{
|
||||
u"file": u"manofsteel-trailer4.mov",
|
||||
u"md5": u"11874af099d480cc09e103b189805d5f",
|
||||
u"info_dict": {
|
||||
u"duration": 111,
|
||||
u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_11624.jpg",
|
||||
u"title": u"Trailer 4",
|
||||
u"upload_date": u"20130523",
|
||||
u"uploader_id": u"wb",
|
||||
},
|
||||
},
|
||||
{
|
||||
u"file": u"manofsteel-trailer3.mov",
|
||||
u"md5": u"07a0a262aae5afe68120eed61137ab34",
|
||||
u"info_dict": {
|
||||
u"duration": 182,
|
||||
u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_10793.jpg",
|
||||
u"title": u"Trailer 3",
|
||||
u"upload_date": u"20130417",
|
||||
u"uploader_id": u"wb",
|
||||
},
|
||||
},
|
||||
{
|
||||
u"file": u"manofsteel-trailer.mov",
|
||||
u"md5": u"e401fde0813008e3307e54b6f384cff1",
|
||||
u"info_dict": {
|
||||
u"duration": 148,
|
||||
u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_8703.jpg",
|
||||
u"title": u"Trailer",
|
||||
u"upload_date": u"20121212",
|
||||
u"uploader_id": u"wb",
|
||||
},
|
||||
},
|
||||
{
|
||||
u"file": u"manofsteel-teaser.mov",
|
||||
u"md5": u"76b392f2ae9e7c98b22913c10a639c97",
|
||||
u"info_dict": {
|
||||
u"duration": 93,
|
||||
u"thumbnail": u"http://trailers.apple.com/trailers/wb/manofsteel/images/thumbnail_6899.jpg",
|
||||
u"title": u"Teaser",
|
||||
u"upload_date": u"20120721",
|
||||
u"uploader_id": u"wb",
|
||||
},
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
movie = mobj.group('movie')
|
||||
uploader_id = mobj.group('company')
|
||||
|
||||
playlist_url = url.partition(u'?')[0] + u'/includes/playlists/web.inc'
|
||||
playlist_snippet = self._download_webpage(playlist_url, movie)
|
||||
playlist_cleaned = re.sub(r'(?s)<script>.*?</script>', u'', playlist_snippet)
|
||||
playlist_html = u'<html>' + playlist_cleaned + u'</html>'
|
||||
|
||||
size_cache = {}
|
||||
|
||||
doc = xml.etree.ElementTree.fromstring(playlist_html)
|
||||
playlist = []
|
||||
for li in doc.findall('./div/ul/li'):
|
||||
title = li.find('.//h3').text
|
||||
video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
|
||||
thumbnail = li.find('.//img').attrib['src']
|
||||
|
||||
date_el = li.find('.//p')
|
||||
upload_date = None
|
||||
m = re.search(r':\s?(?P<month>[0-9]{2})/(?P<day>[0-9]{2})/(?P<year>[0-9]{2})', date_el.text)
|
||||
if m:
|
||||
upload_date = u'20' + m.group('year') + m.group('month') + m.group('day')
|
||||
runtime_el = date_el.find('./br')
|
||||
m = re.search(r':\s?(?P<minutes>[0-9]+):(?P<seconds>[0-9]{1,2})', runtime_el.tail)
|
||||
duration = None
|
||||
if m:
|
||||
duration = 60 * int(m.group('minutes')) + int(m.group('seconds'))
|
||||
|
||||
formats = []
|
||||
for formats_el in li.findall('.//a'):
|
||||
if formats_el.attrib['class'] != 'OverlayPanel':
|
||||
continue
|
||||
target = formats_el.attrib['target']
|
||||
|
||||
format_code = formats_el.text
|
||||
if 'Automatic' in format_code:
|
||||
continue
|
||||
|
||||
size_q = formats_el.attrib['href']
|
||||
size_id = size_q.rpartition('#videos-')[2]
|
||||
if size_id not in size_cache:
|
||||
size_url = url + size_q
|
||||
sizepage_html = self._download_webpage(
|
||||
size_url, movie,
|
||||
note=u'Downloading size info %s' % size_id,
|
||||
errnote=u'Error while downloading size info %s' % size_id,
|
||||
)
|
||||
_doc = xml.etree.ElementTree.fromstring(sizepage_html)
|
||||
size_cache[size_id] = _doc
|
||||
|
||||
sizepage_doc = size_cache[size_id]
|
||||
links = sizepage_doc.findall('.//{http://www.w3.org/1999/xhtml}ul/{http://www.w3.org/1999/xhtml}li/{http://www.w3.org/1999/xhtml}a')
|
||||
for vid_a in links:
|
||||
href = vid_a.get('href')
|
||||
if not href.endswith(target):
|
||||
continue
|
||||
detail_q = href.partition('#')[0]
|
||||
detail_url = url + '/' + detail_q
|
||||
|
||||
m = re.match(r'includes/(?P<detail_id>[^/]+)/', detail_q)
|
||||
detail_id = m.group('detail_id')
|
||||
|
||||
detail_html = self._download_webpage(
|
||||
detail_url, movie,
|
||||
note=u'Downloading detail %s %s' % (detail_id, size_id),
|
||||
errnote=u'Error while downloading detail %s %s' % (detail_id, size_id)
|
||||
)
|
||||
detail_doc = xml.etree.ElementTree.fromstring(detail_html)
|
||||
movie_link_el = detail_doc.find('.//{http://www.w3.org/1999/xhtml}a')
|
||||
assert movie_link_el.get('class') == 'movieLink'
|
||||
movie_link = movie_link_el.get('href').partition('?')[0].replace('_', '_h')
|
||||
ext = determine_ext(movie_link)
|
||||
assert ext == 'mov'
|
||||
|
||||
formats.append({
|
||||
'format': format_code,
|
||||
'ext': ext,
|
||||
'url': movie_link,
|
||||
})
|
||||
|
||||
info = {
|
||||
'_type': 'video',
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'duration': duration,
|
||||
'thumbnail': thumbnail,
|
||||
'upload_date': upload_date,
|
||||
'uploader_id': uploader_id,
|
||||
'user_agent': 'QuickTime compatible (youtube-dl)',
|
||||
}
|
||||
# TODO: Remove when #980 has been merged
|
||||
info['url'] = formats[-1]['url']
|
||||
info['ext'] = formats[-1]['ext']
|
||||
|
||||
playlist.append(info)
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': movie,
|
||||
'entries': playlist,
|
||||
}
|
||||
@ -12,8 +12,8 @@ class C56IE(InfoExtractor):
|
||||
|
||||
_TEST ={
|
||||
u'url': u'http://www.56.com/u39/v_OTM0NDA3MTY.html',
|
||||
u'file': u'93440716.mp4',
|
||||
u'md5': u'9dc07b5c8e978112a6441f9e75d2b59e',
|
||||
u'file': u'93440716.flv',
|
||||
u'md5': u'e59995ac63d0457783ea05f93f12a866',
|
||||
u'info_dict': {
|
||||
u'title': u'网事知多少 第32期：车怒',
|
||||
},
|
||||
|
||||
35
youtube_dl/extractor/canalc2.py
Normal file
35
youtube_dl/extractor/canalc2.py
Normal file
@ -0,0 +1,35 @@
|
||||
# coding: utf-8
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class Canalc2IE(InfoExtractor):
|
||||
_IE_NAME = 'canalc2.tv'
|
||||
_VALID_URL = r'http://.*?\.canalc2\.tv/video\.asp\?idVideo=(\d+)&voir=oui'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://www.canalc2.tv/video.asp?idVideo=12163&voir=oui',
|
||||
u'file': u'12163.mp4',
|
||||
u'md5': u'060158428b650f896c542dfbb3d6487f',
|
||||
u'info_dict': {
|
||||
u'title': u'Terrasses du Numérique'
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = re.match(self._VALID_URL, url).group(1)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
file_name = self._search_regex(
|
||||
r"so\.addVariable\('file','(.*?)'\);",
|
||||
webpage, 'file name')
|
||||
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file_name
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'class="evenement8">(.*?)</a>', webpage, u'title')
|
||||
|
||||
return {'id': video_id,
|
||||
'ext': 'mp4',
|
||||
'url': video_url,
|
||||
'title': title,
|
||||
}
|
||||
@ -5,7 +5,7 @@ from .common import InfoExtractor
|
||||
from ..utils import unified_strdate
|
||||
|
||||
class CanalplusIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.canalplus\.fr/.*?\?vid=(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://(www\.canalplus\.fr/.*?\?vid=|player\.canalplus\.fr/#/)(?P<id>\d+)'
|
||||
_VIDEO_INFO_TEMPLATE = 'http://service.canal-plus.com/video/rest/getVideosLiees/cplus/%s'
|
||||
IE_NAME = u'canalplus.fr'
|
||||
|
||||
|
||||
58
youtube_dl/extractor/cnn.py
Normal file
58
youtube_dl/extractor/cnn.py
Normal file
@ -0,0 +1,58 @@
|
||||
import re
|
||||
import xml.etree.ElementTree
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import determine_ext
|
||||
|
||||
|
||||
class CNNIE(InfoExtractor):
|
||||
_VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/
|
||||
(?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
|
||||
|
||||
_TESTS = [{
|
||||
u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
|
||||
u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
|
||||
u'md5': u'3e6121ea48df7e2259fe73a0628605c4',
|
||||
u'info_dict': {
|
||||
u'title': u'Nadal wins 8th French Open title',
|
||||
u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
|
||||
},
|
||||
},
|
||||
{
|
||||
u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29",
|
||||
u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
|
||||
u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e",
|
||||
u"info_dict": {
|
||||
u"title": "Student's epic speech stuns new freshmen",
|
||||
u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\""
|
||||
}
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
path = mobj.group('path')
|
||||
page_title = mobj.group('title')
|
||||
info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
|
||||
info_xml = self._download_webpage(info_url, page_title)
|
||||
info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8'))
|
||||
|
||||
formats = []
|
||||
for f in info.findall('files/file'):
|
||||
mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate'])
|
||||
if mf is not None:
|
||||
formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text))
|
||||
formats = sorted(formats)
|
||||
(_,_,_, video_path) = formats[-1]
|
||||
video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path
|
||||
|
||||
thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
|
||||
thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
|
||||
|
||||
return {'id': info.attrib['id'],
|
||||
'title': info.find('headline').text,
|
||||
'url': video_url,
|
||||
'ext': determine_ext(video_url),
|
||||
'thumbnail': thumbnails[-1][1],
|
||||
'thumbnails': thumbs_dict,
|
||||
'description': info.find('description').text,
|
||||
}
|
||||
@ -4,6 +4,7 @@ import xml.etree.ElementTree
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urllib_parse_urlparse,
|
||||
determine_ext,
|
||||
|
||||
ExtractorError,
|
||||
)
|
||||
@ -12,7 +13,7 @@ from ..utils import (
|
||||
class CollegeHumorIE(InfoExtractor):
|
||||
_VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
|
||||
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
|
||||
u'file': u'6902724.mp4',
|
||||
u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
|
||||
@ -20,7 +21,16 @@ class CollegeHumorIE(InfoExtractor):
|
||||
u'title': u'Comic-Con Cosplay Catastrophe',
|
||||
u'description': u'Fans get creative this year at San Diego. Too creative. And yes, that\'s really Joss Whedon.',
|
||||
},
|
||||
}
|
||||
},
|
||||
{
|
||||
u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
|
||||
u'file': u'3505939.mp4',
|
||||
u'md5': u'c51ca16b82bb456a4397987791a835f5',
|
||||
u'info_dict': {
|
||||
u'title': u'Font Conference',
|
||||
u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@ -49,25 +59,29 @@ class CollegeHumorIE(InfoExtractor):
|
||||
info['description'] = videoNode.findall('./description')[0].text
|
||||
info['title'] = videoNode.findall('./caption')[0].text
|
||||
info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
|
||||
manifest_url = videoNode.findall('./file')[0].text
|
||||
next_url = videoNode.findall('./file')[0].text
|
||||
except IndexError:
|
||||
raise ExtractorError(u'Invalid metadata XML file')
|
||||
|
||||
manifest_url += '?hdcore=2.10.3'
|
||||
manifestXml = self._download_webpage(manifest_url, video_id,
|
||||
u'Downloading XML manifest',
|
||||
u'Unable to download video info XML')
|
||||
if next_url.endswith(u'manifest.f4m'):
|
||||
manifest_url = next_url + '?hdcore=2.10.3'
|
||||
manifestXml = self._download_webpage(manifest_url, video_id,
|
||||
u'Downloading XML manifest',
|
||||
u'Unable to download video info XML')
|
||||
|
||||
adoc = xml.etree.ElementTree.fromstring(manifestXml)
|
||||
try:
|
||||
media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
|
||||
node_id = media_node.attrib['url']
|
||||
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
|
||||
except IndexError as err:
|
||||
raise ExtractorError(u'Invalid manifest file')
|
||||
adoc = xml.etree.ElementTree.fromstring(manifestXml)
|
||||
try:
|
||||
media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
|
||||
node_id = media_node.attrib['url']
|
||||
video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
|
||||
except IndexError as err:
|
||||
raise ExtractorError(u'Invalid manifest file')
|
||||
url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
|
||||
info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
|
||||
info['ext'] = 'mp4'
|
||||
else:
|
||||
# Old-style direct links
|
||||
info['url'] = next_url
|
||||
info['ext'] = determine_ext(info['url'])
|
||||
|
||||
url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
|
||||
|
||||
info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
|
||||
info['ext'] = 'mp4'
|
||||
return [info]
|
||||
return info
|
||||
|
||||
@ -47,7 +47,8 @@ class InfoExtractor(object):
|
||||
uploader_id: Nickname or id of the video uploader.
|
||||
location: Physical location of the video.
|
||||
player_url: SWF Player URL (used for rtmpdump).
|
||||
subtitles: The subtitle file contents.
|
||||
subtitles: The subtitle file contents as a dictionary in the format
|
||||
{language: subtitles}.
|
||||
view_count: How many users have watched the video on the platform.
|
||||
urlhandle: [internal] The urlHandle to be used to download the file,
|
||||
like returned by urllib.request.urlopen
|
||||
@ -77,7 +78,13 @@ class InfoExtractor(object):
|
||||
@classmethod
|
||||
def suitable(cls, url):
|
||||
"""Receives a URL and returns True if suitable for this IE."""
|
||||
return re.match(cls._VALID_URL, url) is not None
|
||||
|
||||
# This does not use has/getattr intentionally - we want to know whether
|
||||
# we have cached the regexp for *this* class, whereas getattr would also
|
||||
# match the superclass
|
||||
if '_VALID_URL_RE' not in cls.__dict__:
|
||||
cls._VALID_URL_RE = re.compile(cls._VALID_URL)
|
||||
return cls._VALID_URL_RE.match(url) is not None
|
||||
|
||||
@classmethod
|
||||
def working(cls):
|
||||
@ -107,6 +114,11 @@ class InfoExtractor(object):
|
||||
"""Real extraction process. Redefine in subclasses."""
|
||||
pass
|
||||
|
||||
@classmethod
|
||||
def ie_key(cls):
|
||||
"""A string for getting the InfoExtractor with get_info_extractor"""
|
||||
return cls.__name__[:-2]
|
||||
|
||||
@property
|
||||
def IE_NAME(self):
|
||||
return type(self).__name__[:-2]
|
||||
@ -122,7 +134,7 @@ class InfoExtractor(object):
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
if errnote is None:
|
||||
errnote = u'Unable to download webpage'
|
||||
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2])
|
||||
raise ExtractorError(u'%s: %s' % (errnote, compat_str(err)), sys.exc_info()[2], cause=err)
|
||||
|
||||
def _download_webpage_handle(self, url_or_request, video_id, note=None, errnote=None):
|
||||
""" Returns a tuple (page content as string, URL handle) """
|
||||
@ -133,12 +145,17 @@ class InfoExtractor(object):
|
||||
|
||||
urlh = self._request_webpage(url_or_request, video_id, note, errnote)
|
||||
content_type = urlh.headers.get('Content-Type', '')
|
||||
webpage_bytes = urlh.read()
|
||||
m = re.match(r'[a-zA-Z0-9_.-]+/[a-zA-Z0-9_.-]+\s*;\s*charset=(.+)', content_type)
|
||||
if m:
|
||||
encoding = m.group(1)
|
||||
else:
|
||||
encoding = 'utf-8'
|
||||
webpage_bytes = urlh.read()
|
||||
m = re.search(br'<meta[^>]+charset=[\'"]?([^\'")]+)[ /\'">]',
|
||||
webpage_bytes[:1024])
|
||||
if m:
|
||||
encoding = m.group(1).decode('ascii')
|
||||
else:
|
||||
encoding = 'utf-8'
|
||||
if self._downloader.params.get('dump_intermediate_pages', False):
|
||||
try:
|
||||
url = url_or_request.get_full_url()
|
||||
|
||||
@ -21,7 +21,7 @@ class DailymotionIE(InfoExtractor):
|
||||
u'file': u'x33vw9.mp4',
|
||||
u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
|
||||
u'info_dict': {
|
||||
u"uploader": u"Alex and Van .",
|
||||
u"uploader": u"Amphora Alex and Van .",
|
||||
u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
|
||||
}
|
||||
}
|
||||
|
||||
@ -21,17 +21,14 @@ class FunnyOrDieIE(InfoExtractor):
|
||||
video_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_url = self._html_search_regex(r'<video[^>]*>\s*<source[^>]*>\s*<source src="(?P<url>[^"]+)"',
|
||||
video_url = self._search_regex(r'type: "video/mp4", src: "(.*?)"',
|
||||
webpage, u'video URL', flags=re.DOTALL)
|
||||
|
||||
title = self._html_search_regex((r"<h1 class='player_page_h1'.*?>(?P<title>.*?)</h1>",
|
||||
r'<title>(?P<title>[^<]+?)</title>'), webpage, 'title', flags=re.DOTALL)
|
||||
|
||||
info = {
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
'title': title,
|
||||
'title': self._og_search_title(webpage),
|
||||
'description': self._og_search_description(webpage),
|
||||
}
|
||||
return [info]
|
||||
|
||||
@ -8,11 +8,13 @@ from ..utils import (
|
||||
compat_urllib_error,
|
||||
compat_urllib_parse,
|
||||
compat_urllib_request,
|
||||
compat_urlparse,
|
||||
|
||||
ExtractorError,
|
||||
)
|
||||
from .brightcove import BrightcoveIE
|
||||
|
||||
|
||||
class GenericIE(InfoExtractor):
|
||||
IE_DESC = u'Generic downloader that works on some sites'
|
||||
_VALID_URL = r'.*'
|
||||
@ -23,7 +25,7 @@ class GenericIE(InfoExtractor):
|
||||
u'file': u'13601338388002.mp4',
|
||||
u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89',
|
||||
u'info_dict': {
|
||||
u"uploader": u"www.hodiho.fr",
|
||||
u"uploader": u"www.hodiho.fr",
|
||||
u"title": u"R\u00e9gis plante sa Jeep"
|
||||
}
|
||||
},
|
||||
@ -107,8 +109,13 @@ class GenericIE(InfoExtractor):
|
||||
return new_url
|
||||
|
||||
def _real_extract(self, url):
|
||||
new_url = self._test_redirect(url)
|
||||
if new_url: return [self.url_result(new_url)]
|
||||
try:
|
||||
new_url = self._test_redirect(url)
|
||||
if new_url:
|
||||
return [self.url_result(new_url)]
|
||||
except compat_urllib_error.HTTPError:
|
||||
# This may be a stupid server that doesn't like HEAD, our UA, or so
|
||||
pass
|
||||
|
||||
video_id = url.split('/')[-1]
|
||||
try:
|
||||
@ -119,7 +126,7 @@ class GenericIE(InfoExtractor):
|
||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
||||
|
||||
self.report_extraction(video_id)
|
||||
# Look for BrigthCove:
|
||||
# Look for BrightCove:
|
||||
m_brightcove = re.search(r'<object.+?class=([\'"]).*?BrightcoveExperience.*?\1.+?</object>', webpage, re.DOTALL)
|
||||
if m_brightcove is not None:
|
||||
self.to_screen(u'Brightcove video detected.')
|
||||
@ -144,6 +151,9 @@ class GenericIE(InfoExtractor):
|
||||
# We only look in og:video if the MIME type is a video, don't try if it's a Flash player:
|
||||
if m_video_type is not None:
|
||||
mobj = re.search(r'<meta.*?property="og:video".*?content="(.*?)"', webpage)
|
||||
if mobj is None:
|
||||
# HTML5 video
|
||||
mobj = re.search(r'<video[^<]*>.*?<source .*?src="([^"]+)"', webpage, flags=re.DOTALL)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
||||
|
||||
@ -153,6 +163,7 @@ class GenericIE(InfoExtractor):
|
||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
||||
|
||||
video_url = compat_urllib_parse.unquote(mobj.group(1))
|
||||
video_url = compat_urlparse.urljoin(url, video_url)
|
||||
video_id = os.path.basename(video_url)
|
||||
|
||||
# here's a fun little line of code for you:
|
||||
|
||||
@ -57,8 +57,8 @@ class GooglePlusIE(InfoExtractor):
|
||||
webpage, 'title', default=u'NA')
|
||||
|
||||
# Step 2, Simulate clicking the image box to launch video
|
||||
DOMAIN = 'https://plus.google.com'
|
||||
video_page = self._search_regex(r'<a href="((?:%s)?/photos/.*?)"' % re.escape(DOMAIN),
|
||||
DOMAIN = 'https://plus.google.com/'
|
||||
video_page = self._search_regex(r'<a href="((?:%s)?photos/.*?)"' % re.escape(DOMAIN),
|
||||
webpage, u'video page URL')
|
||||
if not video_page.startswith(DOMAIN):
|
||||
video_page = DOMAIN + video_page
|
||||
|
||||
37
youtube_dl/extractor/hark.py
Normal file
37
youtube_dl/extractor/hark.py
Normal file
@ -0,0 +1,37 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import determine_ext
|
||||
|
||||
class HarkIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+'
|
||||
_TEST = {
|
||||
u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
|
||||
u'file': u'mmbzyhkgny.mp3',
|
||||
u'md5': u'6783a58491b47b92c7c1af5a77d4cbee',
|
||||
u'info_dict': {
|
||||
u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013",
|
||||
u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
|
||||
u'duration': 11,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group(1)
|
||||
json_url = "http://www.hark.com/clips/%s.json" %(video_id)
|
||||
info_json = self._download_webpage(json_url, video_id)
|
||||
info = json.loads(info_json)
|
||||
final_url = info['url']
|
||||
|
||||
return {'id': video_id,
|
||||
'url' : final_url,
|
||||
'title': info['name'],
|
||||
'ext': determine_ext(final_url),
|
||||
'description': info['description'],
|
||||
'thumbnail': info['image_original'],
|
||||
'duration': info['duration'],
|
||||
}
|
||||
@ -13,7 +13,7 @@ class IGNIE(InfoExtractor):
|
||||
Some videos of it.ign.com are also supported
|
||||
"""
|
||||
|
||||
_VALID_URL = r'https?://.+?\.ign\.com/(?:videos|show_videos)(/.+)?/(?P<name_or_id>.+)'
|
||||
_VALID_URL = r'https?://.+?\.ign\.com/(?P<type>videos|show_videos|articles)(/.+)?/(?P<name_or_id>.+)'
|
||||
IE_NAME = u'ign.com'
|
||||
|
||||
_CONFIG_URL_TEMPLATE = 'http://www.ign.com/videos/configs/id/%s.config'
|
||||
@ -41,7 +41,11 @@ class IGNIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
name_or_id = mobj.group('name_or_id')
|
||||
page_type = mobj.group('type')
|
||||
webpage = self._download_webpage(url, name_or_id)
|
||||
if page_type == 'articles':
|
||||
video_url = self._search_regex(r'var videoUrl = "(.+?)"', webpage, u'video url')
|
||||
return self.url_result(video_url, ie='IGN')
|
||||
video_id = self._find_video_id(webpage)
|
||||
result = self._get_video_info(video_id)
|
||||
description = self._html_search_regex(self._DESCRIPTION_RE,
|
||||
@ -68,7 +72,7 @@ class IGNIE(InfoExtractor):
|
||||
class OneUPIE(IGNIE):
|
||||
"""Extractor for 1up.com, it uses the ign videos system."""
|
||||
|
||||
_VALID_URL = r'https?://gamevideos.1up.com/video/id/(?P<name_or_id>.+)'
|
||||
_VALID_URL = r'https?://gamevideos.1up.com/(?P<type>video)/id/(?P<name_or_id>.+)'
|
||||
IE_NAME = '1up.com'
|
||||
|
||||
_DESCRIPTION_RE = r'<div id="vid_summary">(.+?)</div>'
|
||||
|
||||
47
youtube_dl/extractor/jeuxvideo.py
Normal file
47
youtube_dl/extractor/jeuxvideo.py
Normal file
@ -0,0 +1,47 @@
|
||||
# coding: utf-8
|
||||
|
||||
import json
|
||||
import re
|
||||
import xml.etree.ElementTree
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
class JeuxVideoIE(InfoExtractor):
|
||||
_VALID_URL = r'http://.*?\.jeuxvideo\.com/.*/(.*?)-\d+\.htm'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://www.jeuxvideo.com/reportages-videos-jeux/0004/00046170/tearaway-playstation-vita-gc-2013-tearaway-nous-presente-ses-papiers-d-identite-00115182.htm',
|
||||
u'file': u'5182.mp4',
|
||||
u'md5': u'e0fdb0cd3ce98713ef9c1e1e025779d0',
|
||||
u'info_dict': {
|
||||
u'title': u'GC 2013 : Tearaway nous présente ses papiers d\'identité',
|
||||
u'description': u'Lorsque les développeurs de LittleBigPlanet proposent un nouveau titre, on ne peut que s\'attendre à un résultat original et fort attrayant.\n',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
title = re.match(self._VALID_URL, url).group(1)
|
||||
webpage = self._download_webpage(url, title)
|
||||
m_download = re.search(r'<param name="flashvars" value="config=(.*?)" />', webpage)
|
||||
|
||||
xml_link = m_download.group(1)
|
||||
|
||||
id = re.search(r'http://www.jeuxvideo.com/config/\w+/0011/(.*?)/\d+_player\.xml', xml_link).group(1)
|
||||
|
||||
xml_config = self._download_webpage(xml_link, title,
|
||||
'Downloading XML config')
|
||||
config = xml.etree.ElementTree.fromstring(xml_config.encode('utf-8'))
|
||||
info = re.search(r'<format\.json>(.*?)</format\.json>',
|
||||
xml_config, re.MULTILINE|re.DOTALL).group(1)
|
||||
info = json.loads(info)['versions'][0]
|
||||
|
||||
video_url = 'http://video720.jeuxvideo.com/' + info['file']
|
||||
|
||||
return {'id': id,
|
||||
'title' : config.find('titre_video').text,
|
||||
'ext' : 'mp4',
|
||||
'url' : video_url,
|
||||
'description': self._og_search_description(webpage),
|
||||
'thumbnail': config.find('image').text,
|
||||
}
|
||||
@ -21,8 +21,10 @@ class KankanIE(InfoExtractor):
|
||||
video_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._search_regex(r'G_TITLE=[\'"](.+?)[\'"]', webpage, u'video title')
|
||||
gcid = self._search_regex(r'lurl:[\'"]http://.+?/.+?/(.+?)/', webpage, u'gcid')
|
||||
title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, u'video title')
|
||||
surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
|
||||
gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
|
||||
gcid = gcids[-1]
|
||||
|
||||
video_info_page = self._download_webpage('http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid,
|
||||
video_id, u'Downloading video url info')
|
||||
|
||||
74
youtube_dl/extractor/mit.py
Normal file
74
youtube_dl/extractor/mit.py
Normal file
@ -0,0 +1,74 @@
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
get_element_by_id,
|
||||
)
|
||||
|
||||
|
||||
class TechTVMITIE(InfoExtractor):
|
||||
IE_NAME = u'techtv.mit.edu'
|
||||
_VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
|
||||
u'file': u'25418.mp4',
|
||||
u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
|
||||
u'info_dict': {
|
||||
u'title': u'MIT DNA Learning Center Set',
|
||||
u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
raw_page = self._download_webpage(
|
||||
'http://techtv.mit.edu/videos/%s' % video_id, video_id)
|
||||
clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
|
||||
|
||||
base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
|
||||
raw_page, u'base url')
|
||||
formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
|
||||
u'video formats')
|
||||
formats = json.loads(formats_json)
|
||||
formats = sorted(formats, key=lambda f: f['bitrate'])
|
||||
|
||||
title = get_element_by_id('edit-title', clean_page)
|
||||
description = clean_html(get_element_by_id('edit-description', clean_page))
|
||||
thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
|
||||
raw_page, u'thumbnail', flags=re.DOTALL)
|
||||
|
||||
return {'id': video_id,
|
||||
'title': title,
|
||||
'url': base_url + formats[-1]['url'].replace('mp4:', ''),
|
||||
'ext': 'mp4',
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
||||
|
||||
class MITIE(TechTVMITIE):
|
||||
IE_NAME = u'video.mit.edu'
|
||||
_VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
|
||||
u'file': u'21783.mp4',
|
||||
u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
|
||||
u'info_dict': {
|
||||
u'title': u'The Government is Profiling You',
|
||||
u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
page_title = mobj.group('title')
|
||||
webpage = self._download_webpage(url, page_title)
|
||||
self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
|
||||
embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
|
||||
u'embed url')
|
||||
return self.url_result(embed_url, ie='TechTVMIT')
|
||||
33
youtube_dl/extractor/nbc.py
Normal file
33
youtube_dl/extractor/nbc.py
Normal file
@ -0,0 +1,33 @@
|
||||
import re
|
||||
import xml.etree.ElementTree
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import find_xpath_attr, compat_str
|
||||
|
||||
|
||||
class NBCNewsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://www.nbcnews.com/video/nbc-news/52753292',
|
||||
u'file': u'52753292.flv',
|
||||
u'md5': u'47abaac93c6eaf9ad37ee6c4463a5179',
|
||||
u'info_dict': {
|
||||
u'title': u'Crew emerges after four-month Mars food study',
|
||||
u'description': u'md5:24e632ffac72b35f8b67a12d1b6ddfc1',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
info_xml = self._download_webpage('http://www.nbcnews.com/id/%s/displaymode/1219' % video_id, video_id)
|
||||
info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')).find('video')
|
||||
|
||||
return {'id': video_id,
|
||||
'title': info.find('headline').text,
|
||||
'ext': 'flv',
|
||||
'url': find_xpath_attr(info, 'media', 'type', 'flashVideo').text,
|
||||
'description': compat_str(info.find('caption').text),
|
||||
'thumbnail': find_xpath_attr(info, 'media', 'type', 'thumbnail').text,
|
||||
}
|
||||
67
youtube_dl/extractor/orf.py
Normal file
67
youtube_dl/extractor/orf.py
Normal file
@ -0,0 +1,67 @@
|
||||
# coding: utf-8
|
||||
|
||||
import re
|
||||
import xml.etree.ElementTree
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urlparse,
|
||||
ExtractorError,
|
||||
find_xpath_attr,
|
||||
)
|
||||
|
||||
class ORFIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://tvthek.orf.at/(programs/.+?/episodes|topics/.+?)/(?P<id>\d+)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://tvthek.orf.at/programs/1171769-Wetter-ZIB/episodes/6557323-Wetter',
|
||||
u'file': u'6566957.flv',
|
||||
u'info_dict': {
|
||||
u'title': u'Wetter',
|
||||
u'description': u'Christa Kummer, Marcus Wadsak und Kollegen präsentieren abwechselnd ihre täglichen Wetterprognosen für Österreich.\r \r Mehr Wetter unter wetter.ORF.at',
|
||||
},
|
||||
u'params': {
|
||||
# It uses rtmp
|
||||
u'skip_download': True,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
playlist_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, playlist_id)
|
||||
|
||||
flash_xml = self._search_regex('ORF.flashXML = \'(.+?)\'', webpage, u'flash xml')
|
||||
flash_xml = compat_urlparse.parse_qs('xml='+flash_xml)['xml'][0]
|
||||
flash_config = xml.etree.ElementTree.fromstring(flash_xml.encode('utf-8'))
|
||||
playlist_json = self._search_regex(r'playlist\': \'(\[.*?\])\'', webpage, u'playlist').replace(r'\"','"')
|
||||
playlist = json.loads(playlist_json)
|
||||
|
||||
videos = []
|
||||
ns = '{http://tempuri.org/XMLSchema.xsd}'
|
||||
xpath = '%(ns)sPlaylist/%(ns)sItems/%(ns)sItem' % {'ns': ns}
|
||||
webpage_description = self._og_search_description(webpage)
|
||||
for (i, (item, info)) in enumerate(zip(flash_config.findall(xpath), playlist), 1):
|
||||
# Get best quality url
|
||||
rtmp_url = None
|
||||
for q in ['Q6A', 'Q4A', 'Q1A']:
|
||||
video_url = find_xpath_attr(item, '%sVideoUrl' % ns, 'quality', q)
|
||||
if video_url is not None:
|
||||
rtmp_url = video_url.text
|
||||
break
|
||||
if rtmp_url is None:
|
||||
raise ExtractorError(u'Couldn\'t get video url: %s' % info['id'])
|
||||
description = self._html_search_regex(
|
||||
r'id="playlist_entry_%s".*?<p>(.*?)</p>' % i, webpage,
|
||||
u'description', default=webpage_description, flags=re.DOTALL)
|
||||
videos.append({
|
||||
'_type': 'video',
|
||||
'id': info['id'],
|
||||
'title': info['title'],
|
||||
'url': rtmp_url,
|
||||
'ext': 'flv',
|
||||
'description': description,
|
||||
})
|
||||
|
||||
return videos
|
||||
34
youtube_dl/extractor/pbs.py
Normal file
34
youtube_dl/extractor/pbs.py
Normal file
@ -0,0 +1,34 @@
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class PBSIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://video.pbs.org/video/(?P<id>\d+)/?'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://video.pbs.org/video/2365006249/',
|
||||
u'file': u'2365006249.mp4',
|
||||
u'md5': 'ce1888486f0908d555a8093cac9a7362',
|
||||
u'info_dict': {
|
||||
u'title': u'A More Perfect Union',
|
||||
u'description': u'md5:ba0c207295339c8d6eced00b7c363c6a',
|
||||
u'duration': 3190,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
|
||||
info_page = self._download_webpage(info_url, video_id)
|
||||
info =json.loads(info_page)
|
||||
return {'id': video_id,
|
||||
'title': info['title'],
|
||||
'url': info['alternate_encoding']['url'],
|
||||
'ext': 'mp4',
|
||||
'description': info['program'].get('description'),
|
||||
'thumbnail': info.get('image_url'),
|
||||
'duration': info.get('duration'),
|
||||
}
|
||||
42
youtube_dl/extractor/ro220.py
Normal file
42
youtube_dl/extractor/ro220.py
Normal file
@ -0,0 +1,42 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
compat_parse_qs,
|
||||
)
|
||||
|
||||
|
||||
class Ro220IE(InfoExtractor):
|
||||
IE_NAME = '220.ro'
|
||||
_VALID_URL = r'(?x)(?:https?://)?(?:www\.)?220\.ro/(?P<category>[^/]+)/(?P<shorttitle>[^/]+)/(?P<video_id>[^/]+)'
|
||||
_TEST = {
|
||||
u"url": u"http://www.220.ro/sport/Luati-Le-Banii-Sez-4-Ep-1/LYV6doKo7f/",
|
||||
u'file': u'LYV6doKo7f.mp4',
|
||||
u'md5': u'03af18b73a07b4088753930db7a34add',
|
||||
u'info_dict': {
|
||||
u"title": u"Luati-le Banii sez 4 ep 1",
|
||||
u"description": u"Iata-ne reveniti dupa o binemeritata vacanta. Va astept si pe Facebook cu pareri si comentarii.",
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('video_id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
flashVars_str = self._search_regex(
|
||||
r'<param name="flashVars" value="([^"]+)"',
|
||||
webpage, u'flashVars')
|
||||
flashVars = compat_parse_qs(flashVars_str)
|
||||
|
||||
info = {
|
||||
'_type': 'video',
|
||||
'id': video_id,
|
||||
'ext': 'mp4',
|
||||
'url': flashVars['videoURL'][0],
|
||||
'title': flashVars['title'][0],
|
||||
'description': clean_html(flashVars['desc'][0]),
|
||||
'thumbnail': flashVars['preview'][0],
|
||||
}
|
||||
return info
|
||||
126
youtube_dl/extractor/rtlnow.py
Normal file
126
youtube_dl/extractor/rtlnow.py
Normal file
@ -0,0 +1,126 @@
|
||||
# encoding: utf-8
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
clean_html,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
class RTLnowIE(InfoExtractor):
|
||||
"""Information Extractor for RTL NOW, RTL2 NOW, SUPER RTL NOW and VOX NOW"""
|
||||
_VALID_URL = r'(?:http://)?(?P<url>(?P<base_url>rtl-now\.rtl\.de/|rtl2now\.rtl2\.de/|(?:www\.)?voxnow\.de/|(?:www\.)?superrtlnow\.de/)[a-zA-Z0-9-]+/[a-zA-Z0-9-]+\.php\?(?:container_id|film_id)=(?P<video_id>[0-9]+)&player=1(?:&season=[0-9]+)?(?:&.*)?)'
|
||||
_TESTS = [{
|
||||
u'url': u'http://rtl-now.rtl.de/ahornallee/folge-1.php?film_id=90419&player=1&season=1',
|
||||
u'file': u'90419.flv',
|
||||
u'info_dict': {
|
||||
u'upload_date': u'20070416',
|
||||
u'title': u'Ahornallee - Folge 1 - Der Einzug',
|
||||
u'description': u'Folge 1 - Der Einzug',
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
u'skip': u'Only works from Germany',
|
||||
},
|
||||
{
|
||||
u'url': u'http://rtl2now.rtl2.de/aerger-im-revier/episode-15-teil-1.php?film_id=69756&player=1&season=2&index=5',
|
||||
u'file': u'69756.flv',
|
||||
u'info_dict': {
|
||||
u'upload_date': u'20120519',
|
||||
u'title': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit...',
|
||||
u'description': u'Ärger im Revier - Ein junger Ladendieb, ein handfester Streit u.a.',
|
||||
u'thumbnail': u'http://autoimg.static-fra.de/rtl2now/219850/1500x1500/image2.jpg',
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
u'skip': u'Only works from Germany',
|
||||
},
|
||||
{
|
||||
u'url': u'www.voxnow.de/voxtours/suedafrika-reporter-ii.php?film_id=13883&player=1&season=17',
|
||||
u'file': u'13883.flv',
|
||||
u'info_dict': {
|
||||
u'upload_date': u'20090627',
|
||||
u'title': u'Voxtours - Südafrika-Reporter II',
|
||||
u'description': u'Südafrika-Reporter II',
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
},
|
||||
{
|
||||
u'url': u'http://superrtlnow.de/medicopter-117/angst.php?film_id=99205&player=1',
|
||||
u'file': u'99205.flv',
|
||||
u'info_dict': {
|
||||
u'upload_date': u'20080928',
|
||||
u'title': u'Medicopter 117 - Angst!',
|
||||
u'description': u'Angst!',
|
||||
u'thumbnail': u'http://autoimg.static-fra.de/superrtlnow/287529/1500x1500/image2.jpg'
|
||||
},
|
||||
u'params': {
|
||||
u'skip_download': True,
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self,url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
|
||||
webpage_url = u'http://' + mobj.group('url')
|
||||
video_page_url = u'http://' + mobj.group('base_url')
|
||||
video_id = mobj.group(u'video_id')
|
||||
|
||||
webpage = self._download_webpage(webpage_url, video_id)
|
||||
|
||||
note_m = re.search(r'''(?sx)
|
||||
<div[ ]style="margin-left:[ ]20px;[ ]font-size:[ ]13px;">(.*?)
|
||||
<div[ ]id="playerteaser">''', webpage)
|
||||
if note_m:
|
||||
msg = clean_html(note_m.group(1))
|
||||
raise ExtractorError(msg)
|
||||
|
||||
video_title = self._html_search_regex(r'<title>(?P<title>[^<]+)</title>',
|
||||
webpage, u'title')
|
||||
playerdata_url = self._html_search_regex(r'\'playerdata\': \'(?P<playerdata_url>[^\']+)\'',
|
||||
webpage, u'playerdata_url')
|
||||
|
||||
playerdata = self._download_webpage(playerdata_url, video_id)
|
||||
mobj = re.search(r'<title><!\[CDATA\[(?P<description>.+?)\s+- (?:Sendung )?vom (?P<upload_date_d>[0-9]{2})\.(?P<upload_date_m>[0-9]{2})\.(?:(?P<upload_date_Y>[0-9]{4})|(?P<upload_date_y>[0-9]{2})) [0-9]{2}:[0-9]{2} Uhr\]\]></title>', playerdata)
|
||||
if mobj:
|
||||
video_description = mobj.group(u'description')
|
||||
if mobj.group('upload_date_Y'):
|
||||
video_upload_date = mobj.group('upload_date_Y')
|
||||
else:
|
||||
video_upload_date = u'20' + mobj.group('upload_date_y')
|
||||
video_upload_date += mobj.group('upload_date_m')+mobj.group('upload_date_d')
|
||||
else:
|
||||
video_description = None
|
||||
video_upload_date = None
|
||||
self._downloader.report_warning(u'Unable to extract description and upload date')
|
||||
|
||||
# Thumbnail: not every video has an thumbnail
|
||||
mobj = re.search(r'<meta property="og:image" content="(?P<thumbnail>[^"]+)">', webpage)
|
||||
if mobj:
|
||||
video_thumbnail = mobj.group(u'thumbnail')
|
||||
else:
|
||||
video_thumbnail = None
|
||||
|
||||
mobj = re.search(r'<filename [^>]+><!\[CDATA\[(?P<url>rtmpe://(?:[^/]+/){2})(?P<play_path>[^\]]+)\]\]></filename>', playerdata)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Unable to extract media URL')
|
||||
video_url = mobj.group(u'url')
|
||||
video_play_path = u'mp4:' + mobj.group(u'play_path')
|
||||
video_player_url = video_page_url + u'includes/vodplayer.swf'
|
||||
|
||||
return [{
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'play_path': video_play_path,
|
||||
'page_url': video_page_url,
|
||||
'player_url': video_player_url,
|
||||
'ext': 'flv',
|
||||
'title': video_title,
|
||||
'description': video_description,
|
||||
'upload_date': video_upload_date,
|
||||
'thumbnail': video_thumbnail,
|
||||
}]
|
||||
23
youtube_dl/extractor/slashdot.py
Normal file
23
youtube_dl/extractor/slashdot.py
Normal file
@ -0,0 +1,23 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class SlashdotIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://tv.slashdot.org/video/\?embed=(?P<id>.*?)(&|$)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://tv.slashdot.org/video/?embed=JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz',
|
||||
u'file': u'JscHMzZDplD0p-yNLOzTfzC3Q3xzJaUz.mp4',
|
||||
u'md5': u'd2222e7a4a4c1541b3e0cf732fb26735',
|
||||
u'info_dict': {
|
||||
u'title': u' Meet the Stampede Supercomputing Cluster\'s Administrator',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
ooyala_url = self._search_regex(r'<script src="(.*?)"', webpage, 'ooyala url')
|
||||
return self.url_result(ooyala_url, 'Ooyala')
|
||||
90
youtube_dl/extractor/sohu.py
Normal file
90
youtube_dl/extractor/sohu.py
Normal file
@ -0,0 +1,90 @@
|
||||
# encoding: utf-8
|
||||
|
||||
import json
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import ExtractorError
|
||||
|
||||
|
||||
class SohuIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://tv\.sohu\.com/\d+?/n(?P<id>\d+)\.shtml.*?'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://tv.sohu.com/20130724/n382479172.shtml#super',
|
||||
u'file': u'382479172.mp4',
|
||||
u'md5': u'bde8d9a6ffd82c63a1eefaef4eeefec7',
|
||||
u'info_dict': {
|
||||
u'title': u'MV：Far East Movement《The Illest》',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
def _fetch_data(vid_id):
|
||||
base_data_url = u'http://hot.vrs.sohu.com/vrs_flash.action?vid='
|
||||
data_url = base_data_url + str(vid_id)
|
||||
data_json = self._download_webpage(
|
||||
data_url, video_id,
|
||||
note=u'Downloading JSON data for ' + str(vid_id))
|
||||
return json.loads(data_json)
|
||||
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
raw_title = self._html_search_regex(r'(?s)<title>(.+?)</title>',
|
||||
webpage, u'video title')
|
||||
title = raw_title.partition('-')[0].strip()
|
||||
|
||||
vid = self._html_search_regex(r'var vid="(\d+)"', webpage,
|
||||
u'video path')
|
||||
data = _fetch_data(vid)
|
||||
|
||||
QUALITIES = ('ori', 'super', 'high', 'nor')
|
||||
vid_ids = [data['data'][q + 'Vid']
|
||||
for q in QUALITIES
|
||||
if data['data'][q + 'Vid'] != 0]
|
||||
if not vid_ids:
|
||||
raise ExtractorError(u'No formats available for this video')
|
||||
|
||||
# For now, we just pick the highest available quality
|
||||
vid_id = vid_ids[-1]
|
||||
|
||||
format_data = data if vid == vid_id else _fetch_data(vid_id)
|
||||
part_count = format_data['data']['totalBlocks']
|
||||
allot = format_data['allot']
|
||||
prot = format_data['prot']
|
||||
clipsURL = format_data['data']['clipsURL']
|
||||
su = format_data['data']['su']
|
||||
|
||||
playlist = []
|
||||
for i in range(part_count):
|
||||
part_url = ('http://%s/?prot=%s&file=%s&new=%s' %
|
||||
(allot, prot, clipsURL[i], su[i]))
|
||||
part_str = self._download_webpage(
|
||||
part_url, video_id,
|
||||
note=u'Downloading part %d of %d' % (i+1, part_count))
|
||||
|
||||
part_info = part_str.split('|')
|
||||
video_url = '%s%s?key=%s' % (part_info[0], su[i], part_info[3])
|
||||
|
||||
video_info = {
|
||||
'id': '%s_part%02d' % (video_id, i + 1),
|
||||
'title': title,
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
}
|
||||
playlist.append(video_info)
|
||||
|
||||
if len(playlist) == 1:
|
||||
info = playlist[0]
|
||||
info['id'] = video_id
|
||||
else:
|
||||
info = {
|
||||
'_type': 'playlist',
|
||||
'entries': playlist,
|
||||
'id': video_id,
|
||||
}
|
||||
|
||||
return info
|
||||
@ -4,6 +4,7 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_str,
|
||||
compat_urlparse,
|
||||
|
||||
ExtractorError,
|
||||
unified_strdate,
|
||||
@ -22,6 +23,7 @@ class SoundcloudIE(InfoExtractor):
|
||||
_VALID_URL = r'''^(?:https?://)?
|
||||
(?:(?:(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)/?(?:[?].*)?$)
|
||||
|(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+))
|
||||
|(?P<widget>w.soundcloud.com/player/?.*?url=.*)
|
||||
)
|
||||
'''
|
||||
IE_NAME = u'soundcloud'
|
||||
@ -79,6 +81,9 @@ class SoundcloudIE(InfoExtractor):
|
||||
if track_id is not None:
|
||||
info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
|
||||
full_title = track_id
|
||||
elif mobj.group('widget'):
|
||||
query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
|
||||
return self.url_result(query['url'][0], ie='Soundcloud')
|
||||
else:
|
||||
# extract uploader (which is in the url)
|
||||
uploader = mobj.group(1)
|
||||
|
||||
@ -5,13 +5,13 @@ from .common import InfoExtractor
|
||||
class StatigramIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:http://)?(?:www\.)?statigr\.am/p/([^/]+)'
|
||||
_TEST = {
|
||||
u'url': u'http://statigr.am/p/484091715184808010_284179915',
|
||||
u'file': u'484091715184808010_284179915.mp4',
|
||||
u'md5': u'deda4ff333abe2e118740321e992605b',
|
||||
u'url': u'http://statigr.am/p/522207370455279102_24101272',
|
||||
u'file': u'522207370455279102_24101272.mp4',
|
||||
u'md5': u'6eb93b882a3ded7c378ee1d6884b1814',
|
||||
u'info_dict': {
|
||||
u"uploader_id": u"videoseconds",
|
||||
u"title": u"Instagram photo by @videoseconds"
|
||||
}
|
||||
u'uploader_id': u'aguynamedpatrick',
|
||||
u'title': u'Instagram photo by @aguynamedpatrick (Patrick Janelle)',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
73
youtube_dl/extractor/trilulilu.py
Normal file
73
youtube_dl/extractor/trilulilu.py
Normal file
@ -0,0 +1,73 @@
|
||||
import json
|
||||
import re
|
||||
import xml.etree.ElementTree
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class TriluliluIE(InfoExtractor):
|
||||
_VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)'
|
||||
_TEST = {
|
||||
u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1",
|
||||
u'file': u"big-buck-bunny-1.mp4",
|
||||
u'info_dict': {
|
||||
u"title": u"Big Buck Bunny",
|
||||
u"description": u":) pentru copilul din noi",
|
||||
},
|
||||
# Server ignores Range headers (--test)
|
||||
u"params": {
|
||||
u"skip_download": True
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('video_id')
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
title = self._og_search_title(webpage)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
description = self._og_search_description(webpage)
|
||||
|
||||
log_str = self._search_regex(
|
||||
r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info')
|
||||
log = json.loads(log_str)
|
||||
|
||||
format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/'
|
||||
u'video-formats2' % log)
|
||||
format_str = self._download_webpage(
|
||||
format_url, video_id,
|
||||
note=u'Downloading formats',
|
||||
errnote=u'Error while downloading formats')
|
||||
|
||||
format_doc = xml.etree.ElementTree.fromstring(format_str)
|
||||
|
||||
video_url_template = (
|
||||
u'http://fs%(server)s.trilulilu.ro/stream.php?type=video'
|
||||
u'&source=site&hash=%(hash)s&username=%(userid)s&'
|
||||
u'key=ministhebest&format=%%s&sig=&exp=' %
|
||||
log)
|
||||
formats = [
|
||||
{
|
||||
'format': fnode.text,
|
||||
'url': video_url_template % fnode.text,
|
||||
}
|
||||
|
||||
for fnode in format_doc.findall('./formats/format')
|
||||
]
|
||||
|
||||
info = {
|
||||
'_type': 'video',
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': title,
|
||||
'description': description,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
||||
# TODO: Remove when #980 has been merged
|
||||
info['url'] = formats[-1]['url']
|
||||
info['ext'] = formats[-1]['format'].partition('-')[0]
|
||||
|
||||
return info
|
||||
32
youtube_dl/extractor/unistra.py
Normal file
32
youtube_dl/extractor/unistra.py
Normal file
@ -0,0 +1,32 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
class UnistraIE(InfoExtractor):
|
||||
_VALID_URL = r'http://utv.unistra.fr/(?:index|video).php\?id_video\=(\d+)'
|
||||
|
||||
_TEST = {
|
||||
u'url': u'http://utv.unistra.fr/video.php?id_video=154',
|
||||
u'file': u'154.mp4',
|
||||
u'md5': u'736f605cfdc96724d55bb543ab3ced24',
|
||||
u'info_dict': {
|
||||
u'title': u'M!ss Yella',
|
||||
u'description': u'md5:104892c71bd48e55d70b902736b81bbf',
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
id = re.match(self._VALID_URL, url).group(1)
|
||||
webpage = self._download_webpage(url, id)
|
||||
file = re.search(r'file: "(.*?)",', webpage).group(1)
|
||||
title = self._html_search_regex(r'<title>UTV - (.*?)</', webpage, u'title')
|
||||
|
||||
video_url = 'http://vod-flash.u-strasbg.fr:8080/' + file
|
||||
|
||||
return {'id': id,
|
||||
'title': title,
|
||||
'ext': 'mp4',
|
||||
'url': video_url,
|
||||
'description': self._html_search_regex(r'<meta name="Description" content="(.*?)"', webpage, u'description', flags=re.DOTALL),
|
||||
'thumbnail': self._search_regex(r'image: "(.*?)"', webpage, u'thumbnail'),
|
||||
}
|
||||
@ -11,14 +11,14 @@ class VevoIE(InfoExtractor):
|
||||
Accepts urls from vevo.com or in the format 'vevo:{id}'
|
||||
(currently used by MTVIE)
|
||||
"""
|
||||
_VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*)$'
|
||||
_VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*?)(\?|$)'
|
||||
_TEST = {
|
||||
u'url': u'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
|
||||
u'file': u'GB1101300280.mp4',
|
||||
u'md5': u'06bea460acb744eab74a9d7dcb4bfd61',
|
||||
u'info_dict': {
|
||||
u"upload_date": u"20130624",
|
||||
u"uploader": u"Hurts",
|
||||
u"upload_date": u"20130624",
|
||||
u"uploader": u"Hurts",
|
||||
u"title": u"Somebody to Die For"
|
||||
}
|
||||
}
|
||||
|
||||
@ -14,7 +14,7 @@ class VideofyMeIE(InfoExtractor):
|
||||
_TEST = {
|
||||
u'url': u'http://www.videofy.me/thisisvideofyme/1100701',
|
||||
u'file': u'1100701.mp4',
|
||||
u'md5': u'2046dd5758541d630bfa93e741e2fd79',
|
||||
u'md5': u'c77d700bdc16ae2e9f3c26019bd96143',
|
||||
u'info_dict': {
|
||||
u'title': u'This is VideofyMe',
|
||||
u'description': None,
|
||||
@ -32,9 +32,8 @@ class VideofyMeIE(InfoExtractor):
|
||||
config = xml.etree.ElementTree.fromstring(config_xml.encode('utf-8'))
|
||||
video = config.find('video')
|
||||
sources = video.find('sources')
|
||||
url_node = find_xpath_attr(sources, 'source', 'id', 'HQ on')
|
||||
if url_node is None:
|
||||
url_node = find_xpath_attr(sources, 'source', 'id', 'HQ off')
|
||||
url_node = next(node for node in [find_xpath_attr(sources, 'source', 'id', 'HQ %s' % key)
|
||||
for key in ['on', 'av', 'off']] if node is not None)
|
||||
video_url = url_node.find('url').text
|
||||
|
||||
return {'id': video_id,
|
||||
|
||||
@ -20,18 +20,31 @@ class VimeoIE(InfoExtractor):
|
||||
_VALID_URL = r'(?P<proto>https?://)?(?:(?:www|player)\.)?vimeo(?P<pro>pro)?\.com/(?:(?:(?:groups|album)/[^/]+)|(?:.*?)/)?(?P<direct_link>play_redirect_hls\?clip_id=)?(?:videos?/)?(?P<id>[0-9]+)(?:[?].*)?$'
|
||||
_NETRC_MACHINE = 'vimeo'
|
||||
IE_NAME = u'vimeo'
|
||||
_TEST = {
|
||||
u'url': u'http://vimeo.com/56015672',
|
||||
u'file': u'56015672.mp4',
|
||||
u'md5': u'8879b6cc097e987f02484baf890129e5',
|
||||
u'info_dict': {
|
||||
u"upload_date": u"20121220",
|
||||
u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
|
||||
u"uploader_id": u"user7108434",
|
||||
u"uploader": u"Filippo Valsorda",
|
||||
u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550"
|
||||
}
|
||||
}
|
||||
_TESTS = [
|
||||
{
|
||||
u'url': u'http://vimeo.com/56015672',
|
||||
u'file': u'56015672.mp4',
|
||||
u'md5': u'8879b6cc097e987f02484baf890129e5',
|
||||
u'info_dict': {
|
||||
u"upload_date": u"20121220",
|
||||
u"description": u"This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
|
||||
u"uploader_id": u"user7108434",
|
||||
u"uploader": u"Filippo Valsorda",
|
||||
u"title": u"youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
|
||||
},
|
||||
},
|
||||
{
|
||||
u'url': u'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
|
||||
u'file': u'68093876.mp4',
|
||||
u'md5': u'3b5ca6aa22b60dfeeadf50b72e44ed82',
|
||||
u'note': u'Vimeo Pro video (#1197)',
|
||||
u'info_dict': {
|
||||
u'uploader_id': u'openstreetmapus',
|
||||
u'uploader': u'OpenStreetMap US',
|
||||
u'title': u'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
def _login(self):
|
||||
(username, password) = self._get_login_info()
|
||||
@ -83,7 +96,9 @@ class VimeoIE(InfoExtractor):
|
||||
video_id = mobj.group('id')
|
||||
if not mobj.group('proto'):
|
||||
url = 'https://' + url
|
||||
if mobj.group('direct_link') or mobj.group('pro'):
|
||||
elif mobj.group('pro'):
|
||||
url = 'http://player.vimeo.com/video/' + video_id
|
||||
elif mobj.group('direct_link'):
|
||||
url = 'https://vimeo.com/' + video_id
|
||||
|
||||
# Retrieve video webpage to extract further information
|
||||
|
||||
@ -6,7 +6,6 @@ import re
|
||||
from .common import InfoExtractor
|
||||
|
||||
from ..utils import (
|
||||
compat_urllib_parse,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
@ -3,7 +3,8 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urllib_parse,
|
||||
|
||||
unescapeHTML,
|
||||
determine_ext,
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
@ -36,15 +37,16 @@ class XHamsterIE(InfoExtractor):
|
||||
video_url = compat_urllib_parse.unquote(mobj.group('file'))
|
||||
else:
|
||||
video_url = mobj.group('server')+'/key='+mobj.group('file')
|
||||
video_extension = video_url.split('.')[-1]
|
||||
|
||||
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
|
||||
webpage, u'title')
|
||||
|
||||
# Can't see the description anywhere in the UI
|
||||
# video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)',
|
||||
# webpage, u'description', fatal=False)
|
||||
# if video_description: video_description = unescapeHTML(video_description)
|
||||
# Only a few videos have an description
|
||||
mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
|
||||
if mobj:
|
||||
video_description = unescapeHTML(mobj.group('description'))
|
||||
else:
|
||||
video_description = None
|
||||
|
||||
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
|
||||
if mobj:
|
||||
@ -62,9 +64,9 @@ class XHamsterIE(InfoExtractor):
|
||||
return [{
|
||||
'id': video_id,
|
||||
'url': video_url,
|
||||
'ext': video_extension,
|
||||
'ext': determine_ext(video_url),
|
||||
'title': video_title,
|
||||
# 'description': video_description,
|
||||
'description': video_description,
|
||||
'upload_date': video_upload_date,
|
||||
'uploader_id': video_uploader_id,
|
||||
'thumbnail': video_thumbnail
|
||||
|
||||
@ -12,14 +12,16 @@ from ..utils import (
|
||||
unescapeHTML,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
from ..aes import (
|
||||
aes_decrypt_text
|
||||
)
|
||||
|
||||
class YouPornIE(InfoExtractor):
|
||||
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
|
||||
_TEST = {
|
||||
u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
|
||||
u'file': u'505835.mp4',
|
||||
u'md5': u'c37ddbaaa39058c76a7e86c6813423c1',
|
||||
u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
|
||||
u'info_dict': {
|
||||
u"upload_date": u"20101221",
|
||||
u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
|
||||
@ -75,7 +77,15 @@ class YouPornIE(InfoExtractor):
|
||||
# Get all of the links from the page
|
||||
LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
|
||||
links = re.findall(LINK_RE, download_list_html)
|
||||
if(len(links) == 0):
|
||||
|
||||
# Get link of hd video if available
|
||||
mobj = re.search(r'var encryptedQuality720URL = \'(?P<encrypted_video_url>[a-zA-Z0-9+/]+={0,2})\';', webpage)
|
||||
if mobj != None:
|
||||
encrypted_video_url = mobj.group(u'encrypted_video_url')
|
||||
video_url = aes_decrypt_text(encrypted_video_url, video_title, 32).decode('utf-8')
|
||||
links = [video_url] + links
|
||||
|
||||
if not links:
|
||||
raise ExtractorError(u'ERROR: no known formats available for video')
|
||||
|
||||
self.to_screen(u'Links found: %d' % len(links))
|
||||
@ -112,7 +122,7 @@ class YouPornIE(InfoExtractor):
|
||||
self._print_formats(formats)
|
||||
return
|
||||
|
||||
req_format = self._downloader.params.get('format', None)
|
||||
req_format = self._downloader.params.get('format', 'best')
|
||||
self.to_screen(u'Format: %s' % req_format)
|
||||
|
||||
if req_format is None or req_format == 'best':
|
||||
|
||||
@ -141,7 +141,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
(?: # the various things that can precede the ID:
|
||||
(?:(?:v|embed|e)/) # v/ or embed/ or e/
|
||||
|(?: # or the v= param in all its forms
|
||||
(?:watch|movie(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
|
||||
(?:(?:watch|movie)(?:_popup)?(?:\.php)?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
|
||||
(?:\?|\#!?) # the params delimiter ? or # or #!
|
||||
(?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx)
|
||||
v=
|
||||
@ -155,11 +155,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
# Listed in order of quality
|
||||
_available_formats = ['38', '37', '46', '22', '45', '35', '44', '34', '18', '43', '6', '5', '17', '13',
|
||||
'95', '94', '93', '92', '132', '151',
|
||||
# 3D
|
||||
'85', '84', '102', '83', '101', '82', '100',
|
||||
# Dash video
|
||||
'138', '137', '248', '136', '247', '135', '246',
|
||||
'245', '244', '134', '243', '133', '242', '160',
|
||||
# Dash audio
|
||||
'141', '172', '140', '171', '139',
|
||||
]
|
||||
_available_formats_prefer_free = ['38', '46', '37', '45', '22', '44', '35', '43', '34', '18', '6', '5', '17', '13',
|
||||
'95', '94', '93', '92', '132', '151',
|
||||
'85', '102', '84', '101', '83', '100', '82',
|
||||
# Dash video
|
||||
'138', '248', '137', '247', '136', '246', '245',
|
||||
'244', '135', '243', '134', '242', '133', '160',
|
||||
# Dash audio
|
||||
'172', '141', '171', '140', '139',
|
||||
]
|
||||
_video_extensions = {
|
||||
'13': '3gp',
|
||||
@ -181,7 +192,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'100': 'webm',
|
||||
'101': 'webm',
|
||||
'102': 'webm',
|
||||
|
||||
|
||||
# videos that use m3u8
|
||||
'92': 'mp4',
|
||||
'93': 'mp4',
|
||||
@ -190,6 +201,29 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'96': 'mp4',
|
||||
'132': 'mp4',
|
||||
'151': 'mp4',
|
||||
|
||||
# Dash mp4
|
||||
'133': 'mp4',
|
||||
'134': 'mp4',
|
||||
'135': 'mp4',
|
||||
'136': 'mp4',
|
||||
'137': 'mp4',
|
||||
'138': 'mp4',
|
||||
'139': 'mp4',
|
||||
'140': 'mp4',
|
||||
'141': 'mp4',
|
||||
'160': 'mp4',
|
||||
|
||||
# Dash webm
|
||||
'171': 'webm',
|
||||
'172': 'webm',
|
||||
'242': 'webm',
|
||||
'243': 'webm',
|
||||
'244': 'webm',
|
||||
'245': 'webm',
|
||||
'246': 'webm',
|
||||
'247': 'webm',
|
||||
'248': 'webm',
|
||||
}
|
||||
_video_dimensions = {
|
||||
'5': '240x400',
|
||||
@ -217,11 +251,58 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
'96': '1080p',
|
||||
'100': '360p',
|
||||
'101': '480p',
|
||||
'102': '720p',
|
||||
'102': '720p',
|
||||
'132': '240p',
|
||||
'151': '72p',
|
||||
'133': '240p',
|
||||
'134': '360p',
|
||||
'135': '480p',
|
||||
'136': '720p',
|
||||
'137': '1080p',
|
||||
'138': '>1080p',
|
||||
'139': '48k',
|
||||
'140': '128k',
|
||||
'141': '256k',
|
||||
'160': '192p',
|
||||
'171': '128k',
|
||||
'172': '256k',
|
||||
'242': '240p',
|
||||
'243': '360p',
|
||||
'244': '480p',
|
||||
'245': '480p',
|
||||
'246': '480p',
|
||||
'247': '720p',
|
||||
'248': '1080p',
|
||||
}
|
||||
_3d_itags = ['85', '84', '102', '83', '101', '82', '100']
|
||||
_special_itags = {
|
||||
'82': '3D',
|
||||
'83': '3D',
|
||||
'84': '3D',
|
||||
'85': '3D',
|
||||
'100': '3D',
|
||||
'101': '3D',
|
||||
'102': '3D',
|
||||
'133': 'DASH Video',
|
||||
'134': 'DASH Video',
|
||||
'135': 'DASH Video',
|
||||
'136': 'DASH Video',
|
||||
'137': 'DASH Video',
|
||||
'138': 'DASH Video',
|
||||
'139': 'DASH Audio',
|
||||
'140': 'DASH Audio',
|
||||
'141': 'DASH Audio',
|
||||
'160': 'DASH Video',
|
||||
'171': 'DASH Audio',
|
||||
'172': 'DASH Audio',
|
||||
'242': 'DASH Video',
|
||||
'243': 'DASH Video',
|
||||
'244': 'DASH Video',
|
||||
'245': 'DASH Video',
|
||||
'246': 'DASH Video',
|
||||
'247': 'DASH Video',
|
||||
'248': 'DASH Video',
|
||||
}
|
||||
|
||||
IE_NAME = u'youtube'
|
||||
_TESTS = [
|
||||
{
|
||||
@ -254,8 +335,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
u"info_dict": {
|
||||
u"upload_date": u"20120506",
|
||||
u"title": u"Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]",
|
||||
u"description": u"md5:b085c9804f5ab69f4adea963a2dceb3c",
|
||||
u"uploader": u"IconaPop",
|
||||
u"description": u"md5:3e2666e0a55044490499ea45fe9037b7",
|
||||
u"uploader": u"Icona Pop",
|
||||
u"uploader_id": u"IconaPop"
|
||||
}
|
||||
},
|
||||
@ -338,21 +419,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
elif len(s) == 89:
|
||||
return s[84:78:-1] + s[87] + s[77:60:-1] + s[0] + s[59:3:-1]
|
||||
elif len(s) == 88:
|
||||
return s[48] + s[81:67:-1] + s[82] + s[66:62:-1] + s[85] + s[61:48:-1] + s[67] + s[47:12:-1] + s[3] + s[11:3:-1] + s[2] + s[12]
|
||||
return s[7:28] + s[87] + s[29:45] + s[55] + s[46:55] + s[2] + s[56:87] + s[28]
|
||||
elif len(s) == 87:
|
||||
return s[6:27] + s[4] + s[28:39] + s[27] + s[40:59] + s[2] + s[60:]
|
||||
elif len(s) == 86:
|
||||
return s[5:20] + s[2] + s[21:]
|
||||
return s[83:36:-1] + s[0] + s[35:2:-1]
|
||||
elif len(s) == 85:
|
||||
return s[83:34:-1] + s[0] + s[33:27:-1] + s[3] + s[26:19:-1] + s[34] + s[18:3:-1] + s[27]
|
||||
elif len(s) == 84:
|
||||
return s[83:27:-1] + s[0] + s[26:5:-1] + s[2:0:-1] + s[27]
|
||||
return s[81:36:-1] + s[0] + s[35:2:-1]
|
||||
elif len(s) == 83:
|
||||
return s[81:64:-1] + s[82] + s[63:52:-1] + s[45] + s[51:45:-1] + s[1] + s[44:1:-1] + s[0]
|
||||
elif len(s) == 82:
|
||||
return s[36] + s[79:67:-1] + s[81] + s[66:40:-1] + s[33] + s[39:36:-1] + s[40] + s[35] + s[0] + s[67] + s[32:0:-1] + s[34]
|
||||
return s[1:19] + s[0] + s[20:68] + s[19] + s[69:82]
|
||||
elif len(s) == 81:
|
||||
return s[56] + s[79:56:-1] + s[41] + s[55:41:-1] + s[80] + s[40:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9]
|
||||
elif len(s) == 80:
|
||||
return s[1:19] + s[0] + s[20:68] + s[19] + s[69:80]
|
||||
elif len(s) == 79:
|
||||
return s[54] + s[77:54:-1] + s[39] + s[53:39:-1] + s[78] + s[38:34:-1] + s[0] + s[33:29:-1] + s[34] + s[28:9:-1] + s[29] + s[8:0:-1] + s[9]
|
||||
|
||||
@ -375,11 +458,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
try:
|
||||
sub_list = compat_urllib_request.urlopen(request).read().decode('utf-8')
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
return (u'unable to download video subtitles: %s' % compat_str(err), None)
|
||||
self._downloader.report_warning(u'unable to download video subtitles: %s' % compat_str(err))
|
||||
return {}
|
||||
sub_lang_list = re.findall(r'name="([^"]*)"[^>]+lang_code="([\w\-]+)"', sub_list)
|
||||
sub_lang_list = dict((l[1], l[0]) for l in sub_lang_list)
|
||||
if not sub_lang_list:
|
||||
return (u'video doesn\'t have subtitles', None)
|
||||
self._downloader.report_warning(u'video doesn\'t have subtitles')
|
||||
return {}
|
||||
return sub_lang_list
|
||||
|
||||
def _list_available_subtitles(self, video_id):
|
||||
@ -388,8 +473,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
|
||||
def _request_subtitle(self, sub_lang, sub_name, video_id, format):
|
||||
"""
|
||||
Return tuple:
|
||||
(error_message, sub_lang, sub)
|
||||
Return the subtitle as a string or None if they are not found
|
||||
"""
|
||||
self.report_video_subtitles_request(video_id, sub_lang, format)
|
||||
params = compat_urllib_parse.urlencode({
|
||||
@ -402,21 +486,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
try:
|
||||
sub = compat_urllib_request.urlopen(url).read().decode('utf-8')
|
||||
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
|
||||
return (u'unable to download video subtitles: %s' % compat_str(err), None, None)
|
||||
self._downloader.report_warning(u'unable to download video subtitles for %s: %s' % (sub_lang, compat_str(err)))
|
||||
return
|
||||
if not sub:
|
||||
return (u'Did not fetch video subtitles', None, None)
|
||||
return (None, sub_lang, sub)
|
||||
self._downloader.report_warning(u'Did not fetch video subtitles')
|
||||
return
|
||||
return sub
|
||||
|
||||
def _request_automatic_caption(self, video_id, webpage):
|
||||
"""We need the webpage for getting the captions url, pass it as an
|
||||
argument to speed up the process."""
|
||||
sub_lang = self._downloader.params.get('subtitleslang') or 'en'
|
||||
sub_lang = (self._downloader.params.get('subtitleslangs') or ['en'])[0]
|
||||
sub_format = self._downloader.params.get('subtitlesformat')
|
||||
self.to_screen(u'%s: Looking for automatic captions' % video_id)
|
||||
mobj = re.search(r';ytplayer.config = ({.*?});', webpage)
|
||||
err_msg = u'Couldn\'t find automatic captions for "%s"' % sub_lang
|
||||
if mobj is None:
|
||||
return [(err_msg, None, None)]
|
||||
self._downloader.report_warning(err_msg)
|
||||
return {}
|
||||
player_config = json.loads(mobj.group(1))
|
||||
try:
|
||||
args = player_config[u'args']
|
||||
@ -431,40 +518,43 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
})
|
||||
subtitles_url = caption_url + '&' + params
|
||||
sub = self._download_webpage(subtitles_url, video_id, u'Downloading automatic captions')
|
||||
return [(None, sub_lang, sub)]
|
||||
except KeyError:
|
||||
return [(err_msg, None, None)]
|
||||
|
||||
def _extract_subtitle(self, video_id):
|
||||
return {sub_lang: sub}
|
||||
# An extractor error can be raise by the download process if there are
|
||||
# no automatic captions but there are subtitles
|
||||
except (KeyError, ExtractorError):
|
||||
self._downloader.report_warning(err_msg)
|
||||
return {}
|
||||
|
||||
def _extract_subtitles(self, video_id):
|
||||
"""
|
||||
Return a list with a tuple:
|
||||
[(error_message, sub_lang, sub)]
|
||||
Return a dictionary: {language: subtitles} or {} if the subtitles
|
||||
couldn't be found
|
||||
"""
|
||||
sub_lang_list = self._get_available_subtitles(video_id)
|
||||
available_subs_list = self._get_available_subtitles(video_id)
|
||||
sub_format = self._downloader.params.get('subtitlesformat')
|
||||
if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
|
||||
return [(sub_lang_list[0], None, None)]
|
||||
if self._downloader.params.get('subtitleslang', False):
|
||||
sub_lang = self._downloader.params.get('subtitleslang')
|
||||
elif 'en' in sub_lang_list:
|
||||
sub_lang = 'en'
|
||||
if not available_subs_list: #There was some error, it didn't get the available subtitles
|
||||
return {}
|
||||
if self._downloader.params.get('allsubtitles', False):
|
||||
sub_lang_list = available_subs_list
|
||||
else:
|
||||
sub_lang = list(sub_lang_list.keys())[0]
|
||||
if not sub_lang in sub_lang_list:
|
||||
return [(u'no closed captions found in the specified language "%s"' % sub_lang, None, None)]
|
||||
if self._downloader.params.get('subtitleslangs', False):
|
||||
reqested_langs = self._downloader.params.get('subtitleslangs')
|
||||
elif 'en' in available_subs_list:
|
||||
reqested_langs = ['en']
|
||||
else:
|
||||
reqested_langs = [list(available_subs_list.keys())[0]]
|
||||
|
||||
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
|
||||
return [subtitle]
|
||||
|
||||
def _extract_all_subtitles(self, video_id):
|
||||
sub_lang_list = self._get_available_subtitles(video_id)
|
||||
sub_format = self._downloader.params.get('subtitlesformat')
|
||||
if isinstance(sub_lang_list,tuple): #There was some error, it didn't get the available subtitles
|
||||
return [(sub_lang_list[0], None, None)]
|
||||
subtitles = []
|
||||
sub_lang_list = {}
|
||||
for sub_lang in reqested_langs:
|
||||
if not sub_lang in available_subs_list:
|
||||
self._downloader.report_warning(u'no closed captions found in the specified language "%s"' % sub_lang)
|
||||
continue
|
||||
sub_lang_list[sub_lang] = available_subs_list[sub_lang]
|
||||
subtitles = {}
|
||||
for sub_lang in sub_lang_list:
|
||||
subtitle = self._request_subtitle(sub_lang, sub_lang_list[sub_lang].encode('utf-8'), video_id, sub_format)
|
||||
subtitles.append(subtitle)
|
||||
if subtitle:
|
||||
subtitles[sub_lang] = subtitle
|
||||
return subtitles
|
||||
|
||||
def _print_formats(self, formats):
|
||||
@ -472,7 +562,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
for x in formats:
|
||||
print('%s\t:\t%s\t[%s]%s' %(x, self._video_extensions.get(x, 'flv'),
|
||||
self._video_dimensions.get(x, '???'),
|
||||
' (3D)' if x in self._3d_itags else ''))
|
||||
' ('+self._special_itags[x]+')' if x in self._special_itags else ''))
|
||||
|
||||
def _extract_id(self, url):
|
||||
mobj = re.match(self._VALID_URL, url, re.VERBOSE)
|
||||
@ -655,25 +745,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
# subtitles
|
||||
video_subtitles = None
|
||||
|
||||
if self._downloader.params.get('writesubtitles', False):
|
||||
video_subtitles = self._extract_subtitle(video_id)
|
||||
if video_subtitles:
|
||||
(sub_error, sub_lang, sub) = video_subtitles[0]
|
||||
if sub_error:
|
||||
self._downloader.report_warning(sub_error)
|
||||
|
||||
if self._downloader.params.get('writeautomaticsub', False):
|
||||
if self._downloader.params.get('writesubtitles', False) or self._downloader.params.get('allsubtitles', False):
|
||||
video_subtitles = self._extract_subtitles(video_id)
|
||||
elif self._downloader.params.get('writeautomaticsub', False):
|
||||
video_subtitles = self._request_automatic_caption(video_id, video_webpage)
|
||||
(sub_error, sub_lang, sub) = video_subtitles[0]
|
||||
if sub_error:
|
||||
self._downloader.report_warning(sub_error)
|
||||
|
||||
if self._downloader.params.get('allsubtitles', False):
|
||||
video_subtitles = self._extract_all_subtitles(video_id)
|
||||
for video_subtitle in video_subtitles:
|
||||
(sub_error, sub_lang, sub) = video_subtitle
|
||||
if sub_error:
|
||||
self._downloader.report_warning(sub_error)
|
||||
|
||||
if self._downloader.params.get('listsubtitles', False):
|
||||
self._list_available_subtitles(video_id)
|
||||
@ -699,6 +774,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
if m_s is not None:
|
||||
self.to_screen(u'%s: Encrypted signatures detected.' % video_id)
|
||||
video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']]
|
||||
m_s = re.search(r'[&,]s=', args.get('adaptive_fmts', u''))
|
||||
if m_s is not None:
|
||||
if 'url_encoded_fmt_stream_map' in video_info:
|
||||
video_info['url_encoded_fmt_stream_map'][0] += ',' + args['adaptive_fmts']
|
||||
else:
|
||||
video_info['url_encoded_fmt_stream_map'] = [args['adaptive_fmts']]
|
||||
elif 'adaptive_fmts' in video_info:
|
||||
if 'url_encoded_fmt_stream_map' in video_info:
|
||||
video_info['url_encoded_fmt_stream_map'][0] += ',' + video_info['adaptive_fmts'][0]
|
||||
else:
|
||||
video_info['url_encoded_fmt_stream_map'] = video_info['adaptive_fmts']
|
||||
except ValueError:
|
||||
pass
|
||||
|
||||
@ -758,7 +844,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
|
||||
video_format = '{0} - {1}{2}'.format(format_param if format_param else video_extension,
|
||||
self._video_dimensions.get(format_param, '???'),
|
||||
' (3D)' if format_param in self._3d_itags else '')
|
||||
' ('+self._special_itags[format_param]+')' if format_param in self._special_itags else '')
|
||||
|
||||
results.append({
|
||||
'id': video_id,
|
||||
|
||||
@ -1,19 +1,20 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import datetime
|
||||
import email.utils
|
||||
import errno
|
||||
import gzip
|
||||
import io
|
||||
import json
|
||||
import locale
|
||||
import os
|
||||
import platform
|
||||
import re
|
||||
import socket
|
||||
import sys
|
||||
import traceback
|
||||
import zlib
|
||||
import email.utils
|
||||
import socket
|
||||
import datetime
|
||||
|
||||
try:
|
||||
import urllib.request as compat_urllib_request
|
||||
@ -60,6 +61,11 @@ try:
|
||||
except ImportError: # Python 2
|
||||
import httplib as compat_http_client
|
||||
|
||||
try:
|
||||
from urllib.error import HTTPError as compat_HTTPError
|
||||
except ImportError: # Python 2
|
||||
from urllib2 import HTTPError as compat_HTTPError
|
||||
|
||||
try:
|
||||
from subprocess import DEVNULL
|
||||
compat_subprocess_get_DEVNULL = lambda: DEVNULL
|
||||
@ -207,7 +213,7 @@ if sys.version_info >= (2,7):
|
||||
def find_xpath_attr(node, xpath, key, val):
|
||||
""" Find the xpath xpath[@key=val] """
|
||||
assert re.match(r'^[a-zA-Z]+$', key)
|
||||
assert re.match(r'^[a-zA-Z@\s]*$', val)
|
||||
assert re.match(r'^[a-zA-Z0-9@\s]*$', val)
|
||||
expr = xpath + u"[@%s='%s']" % (key, val)
|
||||
return node.find(expr)
|
||||
else:
|
||||
@ -489,7 +495,7 @@ def make_HTTPS_handler(opts):
|
||||
|
||||
class ExtractorError(Exception):
|
||||
"""Error during info extraction."""
|
||||
def __init__(self, msg, tb=None, expected=False):
|
||||
def __init__(self, msg, tb=None, expected=False, cause=None):
|
||||
""" tb, if given, is the original traceback (so that it can be printed out).
|
||||
If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
|
||||
"""
|
||||
@ -502,6 +508,7 @@ class ExtractorError(Exception):
|
||||
|
||||
self.traceback = tb
|
||||
self.exc_info = sys.exc_info() # preserve original exception
|
||||
self.cause = cause
|
||||
|
||||
def format_traceback(self):
|
||||
if self.traceback is None:
|
||||
@ -622,8 +629,23 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
|
||||
old_resp = resp
|
||||
# gzip
|
||||
if resp.headers.get('Content-encoding', '') == 'gzip':
|
||||
gz = gzip.GzipFile(fileobj=io.BytesIO(resp.read()), mode='r')
|
||||
resp = self.addinfourl_wrapper(gz, old_resp.headers, old_resp.url, old_resp.code)
|
||||
content = resp.read()
|
||||
gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb')
|
||||
try:
|
||||
uncompressed = io.BytesIO(gz.read())
|
||||
except IOError as original_ioerror:
|
||||
# There may be junk add the end of the file
|
||||
# See http://stackoverflow.com/q/4928560/35070 for details
|
||||
for i in range(1, 1024):
|
||||
try:
|
||||
gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb')
|
||||
uncompressed = io.BytesIO(gz.read())
|
||||
except IOError:
|
||||
continue
|
||||
break
|
||||
else:
|
||||
raise original_ioerror
|
||||
resp = self.addinfourl_wrapper(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
|
||||
resp.msg = old_resp.msg
|
||||
# deflate
|
||||
if resp.headers.get('Content-encoding', '') == 'deflate':
|
||||
@ -657,6 +679,9 @@ def determine_ext(url, default_ext=u'unknown_video'):
|
||||
else:
|
||||
return default_ext
|
||||
|
||||
def subtitles_filename(filename, sub_lang, sub_format):
|
||||
return filename.rsplit('.', 1)[0] + u'.' + sub_lang + u'.' + sub_format
|
||||
|
||||
def date_from_str(date_str):
|
||||
"""
|
||||
Return a datetime object from a string in the format YYYYMMDD or
|
||||
@ -708,3 +733,31 @@ class DateRange(object):
|
||||
return self.start <= date <= self.end
|
||||
def __str__(self):
|
||||
return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())
|
||||
|
||||
|
||||
def platform_name():
|
||||
""" Returns the platform name as a compat_str """
|
||||
res = platform.platform()
|
||||
if isinstance(res, bytes):
|
||||
res = res.decode(preferredencoding())
|
||||
|
||||
assert isinstance(res, compat_str)
|
||||
return res
|
||||
|
||||
|
||||
def bytes_to_intlist(bs):
|
||||
if not bs:
|
||||
return []
|
||||
if isinstance(bs[0], int): # Python 3
|
||||
return list(bs)
|
||||
else:
|
||||
return [ord(c) for c in bs]
|
||||
|
||||
|
||||
def intlist_to_bytes(xs):
|
||||
if not xs:
|
||||
return b''
|
||||
if isinstance(chr(0), bytes): # Python 2
|
||||
return ''.join([chr(x) for x in xs])
|
||||
else:
|
||||
return bytes(xs)
|
||||
|
||||
@ -1,2 +1,2 @@
|
||||
|
||||
__version__ = '2013.08.17'
|
||||
__version__ = '2013.08.29'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user