R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'master' into use-other-downloaders

Browse Source 
Conflicts:
	README.md
	youtube-dl
	youtube_dl/__init__.py
This commit is contained in:
Rogério Brito 2013-05-21 10:56:14 -03:00
commit 03fe9b2e81
23 changed files with 2494 additions and 1401 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

@ -17,4 +17,4 @@ youtube-dl.tar.gz
.coverage
cover/
updates_key.pem
*.egg-info
*.egg-info

1
.travis.yml
View File

@ -8,6 +8,7 @@ notifications:
email:
- filippo.valsorda@gmail.com
- phihag@phihag.de
- jaime.marquinez.ferrandiz+travis@gmail.com
# irc:
# channels:
# - "irc.freenode.org#youtube-dl"

12
Makefile
View File

@ -9,9 +9,19 @@ cleanall: clean
PREFIX=/usr/local
BINDIR=$(PREFIX)/bin
MANDIR=$(PREFIX)/man
SYSCONFDIR=/etc
PYTHON=/usr/bin/env python
# set SYSCONFDIR to /etc if PREFIX=/usr or PREFIX=/usr/local
ifeq ($(PREFIX),/usr)
SYSCONFDIR=/etc
else
ifeq ($(PREFIX),/usr/local)
SYSCONFDIR=/etc
else
SYSCONFDIR=$(PREFIX)/etc
endif
endif
install: youtube-dl youtube-dl.1 youtube-dl.bash-completion
install -d $(DESTDIR)$(BINDIR)
install -m 755 youtube-dl $(DESTDIR)$(BINDIR)

229
README.md
View File

@ -14,113 +14,137 @@ your Unix box, on Windows or on Mac OS X. It is released to the public domain,
which means you can modify it, redistribute it or use it however you like.
# OPTIONS
-h, --help print this help text and exit
--version print program version and exit
-U, --update update this program to latest version
-i, --ignore-errors continue on download errors
-r, --rate-limit LIMIT maximum download rate (e.g. 50k or 44.6m)
-R, --retries RETRIES number of retries (default is 10)
--buffer-size SIZE size of download buffer (e.g. 1024 or 16k) (default
is 1024)
--no-resize-buffer do not automatically adjust the buffer size. By
default, the buffer size is automatically resized
from an initial value of SIZE.
--dump-user-agent display the current browser identification
--user-agent UA specify a custom user agent
--list-extractors List all supported extractors and the URLs they
would handle
-h, --help print this help text and exit
--version print program version and exit
-U, --update update this program to latest version
-i, --ignore-errors continue on download errors
-r, --rate-limit LIMIT maximum download rate (e.g. 50k or 44.6m)
-R, --retries RETRIES number of retries (default is 10)
--buffer-size SIZE size of download buffer (e.g. 1024 or 16k)
(default is 1024)
--no-resize-buffer do not automatically adjust the buffer size. By
default, the buffer size is automatically resized
from an initial value of SIZE.
--dump-user-agent display the current browser identification
--user-agent UA specify a custom user agent
--referer REF specify a custom referer, use if the video access
is restricted to one domain
--list-extractors List all supported extractors and the URLs they
would handle
--proxy URL Use the specified HTTP/HTTPS proxy
--no-check-certificate Suppress HTTPS certificate validation.
## Video Selection:
--playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last)
--match-title REGEX download only matching titles (regex or caseless
sub-string)
--reject-title REGEX skip download for matching titles (regex or
caseless sub-string)
--max-downloads NUMBER Abort after downloading NUMBER files
--min-filesize SIZE Do not download any videos smaller than SIZE (e.g.
50k or 44.6m)
--max-filesize SIZE Do not download any videos larger than SIZE (e.g.
50k or 44.6m)
--playlist-start NUMBER playlist video to start at (default is 1)
--playlist-end NUMBER playlist video to end at (default is last)
--match-title REGEX download only matching titles (regex or caseless
sub-string)
--reject-title REGEX skip download for matching titles (regex or
caseless sub-string)
--max-downloads NUMBER Abort after downloading NUMBER files
--min-filesize SIZE Do not download any videos smaller than SIZE
(e.g. 50k or 44.6m)
--max-filesize SIZE Do not download any videos larger than SIZE (e.g.
50k or 44.6m)
--date DATE download only videos uploaded in this date
--datebefore DATE download only videos uploaded before this date
--dateafter DATE download only videos uploaded after this date
## Filesystem Options:
-t, --title use title in file name
--id use video ID in file name
-l, --literal [deprecated] alias of --title
-A, --auto-number number downloaded files starting from 00000
-o, --output TEMPLATE output filename template. Use %(title)s to get the
title, %(uploader)s for the uploader name,
%(uploader_id)s for the uploader nickname if
different, %(autonumber)s to get an automatically
incremented number, %(ext)s for the filename
extension, %(upload_date)s for the upload date
(YYYYMMDD), %(extractor)s for the provider
(youtube, metacafe, etc), %(id)s for the video id
and %% for a literal percent. Use - to output to
stdout. Can also be used to download to a different
directory, for example with -o '/my/downloads/%(upl
oader)s/%(title)s-%(id)s.%(ext)s' .
--restrict-filenames Restrict filenames to only ASCII characters, and
avoid "&" and spaces in filenames
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
-w, --no-overwrites do not overwrite files
-c, --continue resume partially downloaded files
--no-continue do not resume partially downloaded files (restart
from beginning)
--cookies FILE file to read cookies from and dump cookie jar in
--no-part do not use .part files
--no-mtime do not use the Last-modified header to set the file
modification time
--write-description write video description to a .description file
--write-info-json write video metadata to a .info.json file
-t, --title use title in file name (default)
--id use only video ID in file name
-l, --literal [deprecated] alias of --title
-A, --auto-number number downloaded files starting from 00000
-o, --output TEMPLATE output filename template. Use %(title)s to get
the title, %(uploader)s for the uploader name,
%(uploader_id)s for the uploader nickname if
different, %(autonumber)s to get an automatically
incremented number, %(ext)s for the filename
extension, %(upload_date)s for the upload date
(YYYYMMDD), %(extractor)s for the provider
(youtube, metacafe, etc), %(id)s for the video id
, %(playlist)s for the playlist the video is in,
%(playlist_index)s for the position in the
playlist and %% for a literal percent. Use - to
output to stdout. Can also be used to download to
a different directory, for example with -o '/my/d
ownloads/%(uploader)s/%(title)s-%(id)s.%(ext)s' .
--autonumber-size NUMBER Specifies the number of digits in %(autonumber)s
when it is present in output filename template or
--autonumber option is given
--restrict-filenames Restrict filenames to only ASCII characters, and
avoid "&" and spaces in filenames
-a, --batch-file FILE file containing URLs to download ('-' for stdin)
-w, --no-overwrites do not overwrite files
-c, --continue resume partially downloaded files
--no-continue do not resume partially downloaded files (restart
from beginning)
--cookies FILE file to read cookies from and dump cookie jar in
--no-part do not use .part files
--no-mtime do not use the Last-modified header to set the
file modification time
--write-description write video description to a .description file
--write-info-json write video metadata to a .info.json file
--write-thumbnail write thumbnail image to disk
## Verbosity / Simulation Options:
-q, --quiet activates quiet mode
-s, --simulate do not download the video and do not write anything
to disk
--skip-download do not download the video
-g, --get-url simulate, quiet but print URL
-e, --get-title simulate, quiet but print title
--get-thumbnail simulate, quiet but print thumbnail URL
--get-description simulate, quiet but print video description
--get-filename simulate, quiet but print output filename
--get-format simulate, quiet but print output format
--newline output progress bar as new lines
--no-progress do not print progress bar
--console-title display progress in console titlebar
-v, --verbose print various debugging information
-q, --quiet activates quiet mode
-s, --simulate do not download the video and do not write
anything to disk
--skip-download do not download the video
-g, --get-url simulate, quiet but print URL
-e, --get-title simulate, quiet but print title
--get-id simulate, quiet but print id
--get-thumbnail simulate, quiet but print thumbnail URL
--get-description simulate, quiet but print video description
--get-filename simulate, quiet but print output filename
--get-format simulate, quiet but print output format
--newline output progress bar as new lines
--no-progress do not print progress bar
--console-title display progress in console titlebar
-v, --verbose print various debugging information
--dump-intermediate-pages print downloaded pages to debug problems(very
verbose)
## Video Format Options:
-f, --format FORMAT video format code
--all-formats download all available video formats
--prefer-free-formats prefer free video formats unless a specific one is
requested
--max-quality FORMAT highest quality format to download
-F, --list-formats list all available formats (currently youtube only)
--write-srt write video closed captions to a .srt file
(currently youtube only)
--srt-lang LANG language of the closed captions to download
(optional) use IETF language tags like 'en'
-f, --format FORMAT video format code, specifiy the order of
preference using slashes: "-f 22/17/18"
--all-formats download all available video formats
--prefer-free-formats prefer free video formats unless a specific one
is requested
--max-quality FORMAT highest quality format to download
-F, --list-formats list all available formats (currently youtube
only)
--write-sub write 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)
--list-subs lists all available subtitles for the video
(currently youtube only)
--sub-format LANG subtitle format [srt/sbv] (default=srt)
(currently youtube only)
--sub-lang LANG language of the subtitles to download (optional)
use IETF language tags like 'en'
## Authentication Options:
-u, --username USERNAME account username
-p, --password PASSWORD account password
-n, --netrc use .netrc authentication data
-u, --username USERNAME account username
-p, --password PASSWORD account password
-n, --netrc use .netrc authentication data
## Post-processing Options:
-x, --extract-audio convert video files to audio-only files (requires
ffmpeg or avconv and ffprobe or avprobe)
--audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", "opus", or
"wav"; best by default
--audio-quality QUALITY ffmpeg/avconv audio quality specification, insert a
value between 0 (better) and 9 (worse) for VBR or a
specific bitrate like 128K (default 5)
--recode-video FORMAT Encode the video to another format if necessary
(currently supported: mp4|flv|ogg|webm)
-k, --keep-video keeps the video file on disk after the post-
processing; the video is erased by default
--no-post-overwrites do not overwrite post-processed files; the post-
processed files are overwritten by default
-x, --extract-audio convert video files to audio-only files (requires
ffmpeg or avconv and ffprobe or avprobe)
--audio-format FORMAT "best", "aac", "vorbis", "mp3", "m4a", "opus", or
"wav"; best by default
--audio-quality QUALITY ffmpeg/avconv audio quality specification, insert
a value between 0 (better) and 9 (worse) for VBR
or a specific bitrate like 128K (default 5)
--recode-video FORMAT Encode the video to another format if necessary
(currently supported: mp4|flv|ogg|webm)
-k, --keep-video keeps the video file on disk after the post-
processing; the video is erased by default
--no-post-overwrites do not overwrite post-processed files; the post-
processed files are overwritten by default
# CONFIGURATION
@ -138,6 +162,8 @@ The `-o` option allows users to indicate a template for the output file names. T
- `ext`: The sequence will be replaced by the appropriate extension (like flv or mp4).
- `epoch`: The sequence will be replaced by the Unix epoch when creating the file.
- `autonumber`: The sequence will be replaced by a five-digit number that will be increased with each download, starting at zero.
- `playlist`: The name or the id of the playlist that contains the video.
- `playlist_index`: The index of the video in the playlist, a five-digit number.
The current default template is `%(id)s.%(ext)s`, but that will be switchted to `%(title)s-%(id)s.%(ext)s` (which can be requested with `-t` at the moment).
@ -148,6 +174,19 @@ In some cases, you don't want special characters such as 中, spaces, or &, such
$ youtube-dl --get-filename -o "%(title)s.%(ext)s" BaW_jenozKc --restrict-filenames
youtube-dl_test_video_.mp4 # A simple file name
# VIDEO SELECTION
Videos can be filtered by their upload date using the options `--date`, `--datebefore` or `--dateafter`, they accept dates in two formats:
- Absolute dates: Dates in the format `YYYYMMDD`.
- Relative dates: Dates in the format `(now|today)[+-][0-9](day|week|month|year)(s)?`
Examples:
$ youtube-dl --dateafter now-6months #will only download the videos uploaded in the last 6 months
$ youtube-dl --date 19700101 #will only download the videos uploaded in January 1, 1970
$ youtube-dl --dateafter 20000101 --datebefore 20100101 #will only download the videos uploaded between 2000 and 2010
# FAQ
### Can you please put the -b option back?

57
devscripts/gh-pages/update-feed.py Executable file
View File

@ -0,0 +1,57 @@
#!/usr/bin/env python3
import datetime
import textwrap
import json
atom_template=textwrap.dedent("""\
<?xml version='1.0' encoding='utf-8'?>
<atom:feed xmlns:atom="http://www.w3.org/2005/Atom">
<atom:title>youtube-dl releases</atom:title>
<atom:id>youtube-dl-updates-feed</atom:id>
<atom:updated>@TIMESTAMP@</atom:updated>
@ENTRIES@
</atom:feed>""")
entry_template=textwrap.dedent("""
<atom:entry>
<atom:id>youtube-dl-@VERSION@</atom:id>
<atom:title>New version @VERSION@</atom:title>
<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>
</div>
</atom:content>
<atom:author>
<atom:name>The youtube-dl maintainers</atom:name>
</atom:author>
<atom:updated>@TIMESTAMP@</atom:updated>
</atom:entry>
""")
now = datetime.datetime.now()
now_iso = now.isoformat()
atom_template = atom_template.replace('@TIMESTAMP@',now_iso)
entries=[]
versions_info = json.load(open('update/versions.json'))
versions = list(versions_info['versions'].keys())
versions.sort()
for v in versions:
entry = entry_template.replace('@TIMESTAMP@',v.replace('.','-'))
entry = entry.replace('@VERSION@',v)
entries.append(entry)
entries_str = textwrap.indent(''.join(entries), '\t')
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)

1
devscripts/release.sh
View File

@ -69,6 +69,7 @@ ROOT=$(pwd)
ORIGIN_URL=$(git config --get remote.origin.url)
cd build/gh-pages
"$ROOT/devscripts/gh-pages/add-version.py" $version
"$ROOT/devscripts/gh-pages/update-feed.py"
"$ROOT/devscripts/gh-pages/sign-versions.py" < "$ROOT/updates_key.pem"
"$ROOT/devscripts/gh-pages/generate-download.py"
"$ROOT/devscripts/gh-pages/update-copyright.py"

2
devscripts/transition_helper_exe/youtube-dl.py
View File

@ -40,7 +40,7 @@ raw_input()
filename = sys.argv[0]
UPDATE_URL = "http://rg3.github.com/youtube-dl/update/"
UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
JSON_URL = UPDATE_URL + 'versions.json'
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)

8
test/parameters.json
View File

@ -29,6 +29,7 @@
"simulate": false,
"skip_download": false,
"subtitleslang": null,
"subtitlesformat": "srt",
"test": true,
"updatetime": true,
"usenetrc": false,
@ -36,5 +37,8 @@
"verbose": true,
"writedescription": false,
"writeinfojson": true,
"writesubtitles": false
}
"writesubtitles": false,
"onlysubtitles": false,
"allsubtitles": false,
"listssubtitles": false
}

7
test/test_all_urls.py
View File

@ -7,7 +7,7 @@ import unittest
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE
from youtube_dl.InfoExtractors import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE
class TestAllURLsMatching(unittest.TestCase):
def test_youtube_playlist_matching(self):
@ -24,6 +24,11 @@ class TestAllURLsMatching(unittest.TestCase):
self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M'))
self.assertFalse(YoutubeIE.suitable(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
def test_youtube_channel_matching(self):
self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM'))
self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec'))
self.assertTrue(YoutubeChannelIE.suitable('https://www.youtube.com/channel/HCtnHdj3df7iM/videos'))
def test_youtube_extract(self):
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')

24
test/test_download.py
View File

@ -20,6 +20,8 @@ from youtube_dl.utils import *
DEF_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tests.json')
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
RETRIES = 3
# General configuration (from __init__, not very elegant...)
jar = compat_cookiejar.CookieJar()
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
@ -56,6 +58,7 @@ with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
class TestDownload(unittest.TestCase):
maxDiff = None
def setUp(self):
self.parameters = parameters
self.defs = defs
@ -64,7 +67,7 @@ class TestDownload(unittest.TestCase):
def generator(test_case):
def test_template(self):
ie = getattr(youtube_dl.InfoExtractors, test_case['name'] + 'IE')
ie = youtube_dl.InfoExtractors.get_info_extractor(test_case['name'])
if not ie._WORKING:
print('Skipping: IE marked as not _WORKING')
return
@ -79,9 +82,8 @@ def generator(test_case):
params.update(test_case.get('params', {}))
fd = FileDownloader(params)
fd.add_info_extractor(ie())
for ien in test_case.get('add_ie', []):
fd.add_info_extractor(getattr(youtube_dl.InfoExtractors, ien + 'IE')())
for ie in youtube_dl.InfoExtractors.gen_extractors():
fd.add_info_extractor(ie)
finished_hook_called = set()
def _hook(status):
if status['status'] == 'finished':
@ -94,7 +96,19 @@ def generator(test_case):
_try_rm(tc['file'] + '.part')
_try_rm(tc['file'] + '.info.json')
try:
fd.download([test_case['url']])
for retry in range(1, RETRIES + 1):
try:
fd.download([test_case['url']])
except (DownloadError, ExtractorError) as err:
if retry == RETRIES: raise
# Check if the exception is not a network related one
if not err.exc_info[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
raise
print('Retrying: {0} failed tries\n\n##########\n\n'.format(retry))
else:
break
for tc in test_cases:
if not test_case.get('params', {}).get('skip_download', False):

16
test/test_utils.py
View File

@ -14,6 +14,8 @@ from youtube_dl.utils import timeconvert
from youtube_dl.utils import sanitize_filename
from youtube_dl.utils import unescapeHTML
from youtube_dl.utils import orderedSet
from youtube_dl.utils import DateRange
from youtube_dl.utils import unified_strdate
if sys.version_info < (3, 0):
_compat_str = lambda b: b.decode('unicode-escape')
@ -95,6 +97,20 @@ class TestUtil(unittest.TestCase):
def test_unescape_html(self):
self.assertEqual(unescapeHTML(_compat_str('%20;')), _compat_str('%20;'))
def test_daterange(self):
_20century = DateRange("19000101","20000101")
self.assertFalse("17890714" in _20century)
_ac = DateRange("00010101")
self.assertTrue("19690721" in _ac)
_firstmilenium = DateRange(end="10000101")
self.assertTrue("07110427" in _firstmilenium)
def test_unified_dates(self):
self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
self.assertEqual(unified_strdate('8/7/2009'), '20090708')
self.assertEqual(unified_strdate('Dec 14, 2012'), '20121214')
self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
if __name__ == '__main__':
unittest.main()

66
test/test_youtube_lists.py
View File

@ -8,8 +8,9 @@ import json
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.InfoExtractors import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE
from youtube_dl.InfoExtractors import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE
from youtube_dl.utils import *
from youtube_dl.FileDownloader import FileDownloader
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
@ -22,64 +23,87 @@ proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
class FakeDownloader(object):
class FakeDownloader(FileDownloader):
def __init__(self):
self.result = []
self.params = parameters
def to_screen(self, s):
print(s)
def trouble(self, s):
def trouble(self, s, tb=None):
raise Exception(s)
def download(self, x):
self.result.append(x)
def extract_info(self, url):
self.result.append(url)
return url
class TestYoutubeLists(unittest.TestCase):
def assertIsPlaylist(self,info):
"""Make sure the info has '_type' set to 'playlist'"""
self.assertEqual(info['_type'], 'playlist')
def test_youtube_playlist(self):
dl = FakeDownloader()
ie = YoutubePlaylistIE(dl)
ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')
ytie_results = [YoutubeIE()._extract_id(r[0]) for r in dl.result]
result = ie.extract('https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re')[0]
self.assertIsPlaylist(result)
self.assertEqual(result['title'], 'ytdl test PL')
ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
self.assertEqual(ytie_results, [ 'bV9L5Ht9LgY', 'FXxLjLQi3Fg', 'tU3Bgo5qJZE'])
def test_issue_673(self):
dl = FakeDownloader()
ie = YoutubePlaylistIE(dl)
ie.extract('PLBB231211A4F62143')
self.assertTrue(len(dl.result) > 40)
result = ie.extract('PLBB231211A4F62143')[0]
self.assertEqual(result['title'], 'Team Fortress 2')
self.assertTrue(len(result['entries']) > 40)
def test_youtube_playlist_long(self):
dl = FakeDownloader()
ie = YoutubePlaylistIE(dl)
ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
self.assertTrue(len(dl.result) >= 799)
result = ie.extract('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')[0]
self.assertIsPlaylist(result)
self.assertTrue(len(result['entries']) >= 799)
def test_youtube_playlist_with_deleted(self):
#651
dl = FakeDownloader()
ie = YoutubePlaylistIE(dl)
ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
ytie_results = [YoutubeIE()._extract_id(r[0]) for r in dl.result]
result = ie.extract('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')[0]
ytie_results = [YoutubeIE()._extract_id(url['url']) for url in result['entries']]
self.assertFalse('pElCt5oNDuI' in ytie_results)
self.assertFalse('KdPEApIVdWM' in ytie_results)
def test_youtube_playlist_empty(self):
dl = FakeDownloader()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx')[0]
self.assertIsPlaylist(result)
self.assertEqual(len(result['entries']), 0)
def test_youtube_course(self):
dl = FakeDownloader()
ie = YoutubePlaylistIE(dl)
# TODO find a > 100 (paginating?) videos course
ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
self.assertEqual(YoutubeIE()._extract_id(dl.result[0][0]), 'j9WZyLZCBzs')
self.assertEqual(len(dl.result), 25)
self.assertEqual(YoutubeIE()._extract_id(dl.result[-1][0]), 'rYefUsYuEp0')
result = ie.extract('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')[0]
entries = result['entries']
self.assertEqual(YoutubeIE()._extract_id(entries[0]['url']), 'j9WZyLZCBzs')
self.assertEqual(len(entries), 25)
self.assertEqual(YoutubeIE()._extract_id(entries[-1]['url']), 'rYefUsYuEp0')
def test_youtube_channel(self):
# I give up, please find a channel that does paginate and test this like test_youtube_playlist_long
pass # TODO
dl = FakeDownloader()
ie = YoutubeChannelIE(dl)
#test paginated channel
result = ie.extract('https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w')[0]
self.assertTrue(len(result['entries']) > 90)
#test autogenerated channel
result = ie.extract('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')[0]
self.assertTrue(len(result['entries']) >= 18)
def test_youtube_user(self):
dl = FakeDownloader()
ie = YoutubeUserIE(dl)
ie.extract('https://www.youtube.com/user/TheLinuxFoundation')
self.assertTrue(len(dl.result) >= 320)
result = ie.extract('https://www.youtube.com/user/TheLinuxFoundation')[0]
self.assertTrue(len(result['entries']) >= 320)
if __name__ == '__main__':
unittest.main()

54
test/test_youtube_subtitles.py
View File

@ -12,6 +12,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.InfoExtractors import YoutubeIE
from youtube_dl.utils import *
from youtube_dl import FileDownloader
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
@ -24,13 +25,13 @@ proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
class FakeDownloader(object):
class FakeDownloader(FileDownloader):
def __init__(self):
self.result = []
self.params = parameters
def to_screen(self, s):
print(s)
def trouble(self, s):
def trouble(self, s, tb=None):
raise Exception(s)
def download(self, x):
self.result.append(x)
@ -38,20 +39,63 @@ class FakeDownloader(object):
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
class TestYoutubeSubtitles(unittest.TestCase):
def setUp(self):
DL = FakeDownloader()
DL.params['allsubtitles'] = False
DL.params['writesubtitles'] = False
DL.params['subtitlesformat'] = 'srt'
DL.params['listsubtitles'] = False
def test_youtube_no_subtitles(self):
DL = FakeDownloader()
DL.params['writesubtitles'] = False
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
subtitles = info_dict[0]['subtitles']
self.assertEqual(subtitles, None)
def test_youtube_subtitles(self):
DL = FakeDownloader()
DL.params['writesubtitles'] = True
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
self.assertEqual(md5(info_dict[0]['subtitles']), 'c3228550d59116f3c29fba370b55d033')
sub = info_dict[0]['subtitles'][0]
self.assertEqual(md5(sub[2]), '4cd9278a35ba2305f47354ee13472260')
def test_youtube_subtitles_it(self):
DL = FakeDownloader()
DL.params['writesubtitles'] = True
DL.params['subtitleslang'] = 'it'
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
self.assertEqual(md5(info_dict[0]['subtitles']), '132a88a0daf8e1520f393eb58f1f646a')
sub = info_dict[0]['subtitles'][0]
self.assertEqual(md5(sub[2]), '164a51f16f260476a05b50fe4c2f161d')
def test_youtube_onlysubtitles(self):
DL = FakeDownloader()
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')
def test_youtube_allsubtitles(self):
DL = FakeDownloader()
DL.params['allsubtitles'] = True
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
subtitles = info_dict[0]['subtitles']
self.assertEqual(len(subtitles), 13)
def test_youtube_subtitles_format(self):
DL = FakeDownloader()
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')
def test_youtube_list_subtitles(self):
DL = FakeDownloader()
DL.params['listsubtitles'] = True
IE = YoutubeIE(DL)
info_dict = IE.extract('QRS8MkLhQmM')
self.assertEqual(info_dict, None)
if __name__ == '__main__':
unittest.main()

195
test/tests.json
View File

@ -76,8 +76,7 @@
"name": "StanfordOpenClassroom",
"md5": "544a9468546059d4e80d76265b0443b8",
"url": "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100",
"file": "PracticalUnix_intro-environment.mp4",
"skip": "Currently offline"
"file": "PracticalUnix_intro-environment.mp4"
},
{
"name": "XNXX",
@ -113,9 +112,8 @@
{
"name": "Escapist",
"url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate",
"file": "6618-Breaking-Down-Baldurs-Gate.flv",
"md5": "c6793dbda81388f4264c1ba18684a74d",
"skip": "Fails with timeout on Travis"
"file": "6618-Breaking-Down-Baldurs-Gate.mp4",
"md5": "c6793dbda81388f4264c1ba18684a74d"
},
{
"name": "GooglePlus",
@ -154,7 +152,8 @@
"file": "20274954.flv",
"md5": "088f151799e8f572f84eb62f17d73e5c",
"info_dict": {
"title": "Young Americans for Liberty February 7, 2012 2:28 AM"
"title": "Young Americans for Liberty February 7, 2012 2:28 AM",
"uploader": "Young Americans for Liberty"
}
},
{
@ -299,5 +298,189 @@
"url": "http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html",
"file": "13601338388002.mp4",
"md5": "85b90ccc9d73b4acd9138d3af4c27f89"
},
{
"name": "Spiegel",
"url": "http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html",
"file": "1259285.mp4",
"md5": "2c2754212136f35fb4b19767d242f66e",
"info_dict": {
"title": "Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
}
},
{
"name": "LiveLeak",
"md5": "0813c2430bea7a46bf13acf3406992f4",
"url": "http://www.liveleak.com/view?i=757_1364311680",
"file": "757_1364311680.mp4",
"info_dict": {
"title": "Most unlucky car accident",
"description": "extremely bad day for this guy..!",
"uploader": "ljfriel2"
}
},
{
"name": "WorldStarHipHop",
"url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
"file": "wshh6a7q1ny0G34ZwuIO.mp4",
"md5": "9d04de741161603bf7071bbf4e883186",
"info_dict": {
"title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick! "
}
},
{
"name": "ARD",
"url": "http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640",
"file": "14077640.mp4",
"md5": "6ca8824255460c787376353f9e20bbd8",
"info_dict": {
"title": "11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
},
"skip": "Requires rtmpdump"
},
{
"name": "Tumblr",
"url": "http://birthdayproject2012.tumblr.com/post/17258355236/a-sample-video-from-leeann-if-you-need-an-idea",
"file": "17258355236.mp4",
"md5": "7c6a514d691b034ccf8567999e9e88a3",
"info_dict": {
"title": "Calling all Pris! - A sample video from LeeAnn. (If you need an idea..."
}
},
{
"name": "SoundcloudSet",
"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
"playlist":[
{
"file":"30510138.mp3",
"md5":"f9136bf103901728f29e419d2c70f55d",
"info_dict": {
"title":"D-D-Dance"
}
},
{
"file":"47127625.mp3",
"md5":"09b6758a018470570f8fd423c9453dd8",
"info_dict": {
"title":"The Royal Concept - Gimme Twice"
}
},
{
"file":"47127627.mp3",
"md5":"154abd4e418cea19c3b901f1e1306d9c",
"info_dict": {
"title":"Goldrushed"
}
},
{
"file":"47127629.mp3",
"md5":"2f5471edc79ad3f33a683153e96a79c1",
"info_dict": {
"title":"In the End"
}
},
{
"file":"47127631.mp3",
"md5":"f9ba87aa940af7213f98949254f1c6e2",
"info_dict": {
"title":"Knocked Up"
}
},
{
"file":"75206121.mp3",
"md5":"f9d1fe9406717e302980c30de4af9353",
"info_dict": {
"title":"World On Fire"
}
}
]
},
{
"name":"Bandcamp",
"url":"http://youtube-dl.bandcamp.com/track/youtube-dl-test-song",
"file":"1812978515.mp3",
"md5":"cdeb30cdae1921719a3cbcab696ef53c",
"info_dict": {
"title":"youtube-dl test song \"'/\\ä↭"
},
"skip": "There is a limit of 200 free downloads / month for the test song"
},
{
"name": "RedTube",
"url": "http://www.redtube.com/66418",
"file": "66418.mp4",
"md5": "7b8c22b5e7098a3e1c09709df1126d2d",
"info_dict":{
"title":"Sucked on a toilet"
}
},
{
"name": "Photobucket",
"url": "http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0",
"file": "zpsc0c3b9fa.mp4",
"md5": "7dabfb92b0a31f6c16cebc0f8e60ff99",
"info_dict":{
"title":"Tired of Link Building? Try BacklinkMyDomain.com!"
}
},
{
"name": "Ina",
"url": "www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html",
"file": "I12055569.mp4",
"md5": "a667021bf2b41f8dc6049479d9bb38a3",
"info_dict":{
"title":"François Hollande \"Je crois que c'est clair\""
}
},
{
"name": "Yahoo",
"url": "http://screen.yahoo.com/obama-celebrates-iraq-victory-27592561.html",
"file": "27592561.flv",
"md5": "c6179bed843512823fd284fa2e7f012d",
"info_dict": {
"title": "Obama Celebrates Iraq Victory"
},
"skip": "Requires rtmpdump"
},
{
"name": "Howcast",
"url": "http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly",
"file": "390161.mp4",
"md5": "1d7ba54e2c9d7dc6935ef39e00529138",
"info_dict":{
"title":"How to Tie a Square Knot Properly",
"description":"The square knot, also known as the reef knot, is one of the oldest, most basic knots to tie, and can be used in many different ways. Here's the proper way to tie a square knot."
}
},
{
"name": "Vine",
"url": "https://vine.co/v/b9KOOWX7HUx",
"file": "b9KOOWX7HUx.mp4",
"md5": "2f36fed6235b16da96ce9b4dc890940d",
"info_dict":{
"title": "Chicken.",
"uploader": "Jack Dorsey"
}
},
{
"name": "Flickr",
"url": "http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/",
"file": "5645318632.mp4",
"md5": "6fdc01adbc89d72fc9c4f15b4a4ba87b",
"info_dict":{
"title": "Dark Hollow Waterfalls",
"uploader_id": "forestwander-nature-pictures",
"description": "Waterfalls in the Springtime at Dark Hollow Waterfalls. These are located just off of Skyline Drive in Virginia. They are only about 6/10 of a mile hike but it is a pretty steep hill and a good climb back up."
}
},
{
"name": "Teamcoco",
"url": "http://teamcoco.com/video/louis-ck-interview-george-w-bush",
"file": "19705.mp4",
"md5": "27b6f7527da5acf534b15f21b032656e",
"info_dict":{
"title": "Louis C.K. Interview Pt. 1 11/3/11",
"description": "Louis C.K. got starstruck by George W. Bush, so what? Part one."
}
}
]

BIN
youtube-dl
View File

Binary file not shown.

348
youtube_dl/FileDownloader.py
View File

@ -7,6 +7,7 @@ import math
import io
import os
import re
import shutil
import socket
import subprocess
import sys
@ -17,6 +18,7 @@ if os.name == 'nt':
import ctypes
from .utils import *
from .InfoExtractors import get_info_extractor
class FileDownloader(object):
@ -52,6 +54,7 @@ class FileDownloader(object):
quiet: Do not print messages to stdout.
forceurl: Force printing final URL.
forcetitle: Force printing title.
forceid: Force printing ID.
forcethumbnail: Force printing thumbnail URL.
forcedescription: Force printing description.
forcefilename: Force printing final filename.
@ -78,12 +81,18 @@ class FileDownloader(object):
updatetime: Use the Last-modified header to set output file timestamps.
writedescription: Write the video description to a .description file
writeinfojson: Write the video description to a .info.json file
writesubtitles: Write the video subtitles to a .srt file
writethumbnail: Write the thumbnail image to a file
writesubtitles: Write the video subtitles to a file
allsubtitles: Downloads all the subtitles of the video
listsubtitles: Lists all available subtitles for the video
subtitlesformat: Subtitle format [sbv/srt] (default=srt)
subtitleslang: Language of the subtitles to download
test: Download only first bytes to test the downloader.
keepvideo: Keep the video file after post-processing
min_filesize: Skip files smaller than this size
max_filesize: Skip files larger than this size
daterange: A DateRange object, download only if the upload_date is in the range.
skip_download: Skip the actual download of the video file
"""
params = None
@ -116,7 +125,7 @@ class FileDownloader(object):
exponent = 0
else:
exponent = int(math.log(bytes, 1024.0))
suffix = 'bkMGTPEZY'[exponent]
suffix = ['B','KiB','MiB','GiB','TiB','PiB','EiB','ZiB','YiB'][exponent]
converted = float(bytes) / float(1024 ** exponent)
return '%.2f%s' % (converted, suffix)
@ -227,11 +236,21 @@ class FileDownloader(object):
self.to_stderr(message)
if self.params.get('verbose'):
if tb is None:
tb_data = traceback.format_list(traceback.extract_stack())
tb = u''.join(tb_data)
if sys.exc_info()[0]: # if .trouble has been called from an except block
tb = u''
if hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
tb += u''.join(traceback.format_exception(*sys.exc_info()[1].exc_info))
tb += compat_str(traceback.format_exc())
else:
tb_data = traceback.format_list(traceback.extract_stack())
tb = u''.join(tb_data)
self.to_stderr(tb)
if not self.params.get('ignoreerrors', False):
raise DownloadError(message)
if sys.exc_info()[0] and hasattr(sys.exc_info()[1], 'exc_info') and sys.exc_info()[1].exc_info[0]:
exc_info = sys.exc_info()[1].exc_info
else:
exc_info = sys.exc_info()
raise DownloadError(message, exc_info)
self._download_retcode = 1
def report_warning(self, message):
@ -239,13 +258,25 @@ class FileDownloader(object):
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
if sys.stderr.isatty():
if sys.stderr.isatty() and os.name != 'nt':
_msg_header=u'\033[0;33mWARNING:\033[0m'
else:
_msg_header=u'WARNING:'
warning_message=u'%s %s' % (_msg_header,message)
self.to_stderr(warning_message)
def report_error(self, message, tb=None):
'''
Do the same as trouble, but prefixes the message with 'ERROR:', colored
in red if stderr is a tty file.
'''
if sys.stderr.isatty() and os.name != 'nt':
_msg_header = u'\033[0;31mERROR:\033[0m'
else:
_msg_header = u'ERROR:'
error_message = u'%s %s' % (_msg_header, message)
self.trouble(error_message, tb)
def slow_down(self, start_time, byte_counter):
"""Sleep if the download speed is over the rate limit."""
rate_limit = self.params.get('ratelimit', None)
@ -277,7 +308,7 @@ class FileDownloader(object):
return
os.rename(encodeFilename(old_filename), encodeFilename(new_filename))
except (IOError, OSError) as err:
self.trouble(u'ERROR: unable to rename file')
self.report_error(u'unable to rename file')
def try_utime(self, filename, last_modified_hdr):
"""Try to set the last-modified time of the given file."""
@ -301,9 +332,9 @@ class FileDownloader(object):
""" Report that the description file is being written """
self.to_screen(u'[info] Writing video description to: ' + descfn)
def report_writesubtitles(self, srtfn):
def report_writesubtitles(self, sub_filename):
""" Report that the subtitles file is being written """
self.to_screen(u'[info] Writing video subtitles to: ' + srtfn)
self.to_screen(u'[info] Writing video subtitles to: ' + sub_filename)
def report_writeinfojson(self, infofn):
""" Report that the metadata file has been written """
@ -317,12 +348,13 @@ class FileDownloader(object):
"""Report download progress."""
if self.params.get('noprogress', False):
return
clear_line = (u'\x1b[K' if sys.stderr.isatty() and os.name != 'nt' else u'')
if self.params.get('progress_with_newline', False):
self.to_screen(u'[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str))
else:
self.to_screen(u'\r[download] %s of %s at %s ETA %s' %
(percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
self.to_screen(u'\r%s[download] %s of %s at %s ETA %s' %
(clear_line, percent_str, data_len_str, speed_str, eta_str), skip_eol=True)
self.to_cons_title(u'youtube-dl - %s of %s at %s ETA %s' %
(percent_str.strip(), data_len_str.strip(), speed_str.strip(), eta_str.strip()))
@ -362,7 +394,13 @@ class FileDownloader(object):
template_dict = dict(info_dict)
template_dict['epoch'] = int(time.time())
template_dict['autonumber'] = u'%05d' % self._num_downloads
autonumber_size = self.params.get('autonumber_size')
if autonumber_size is None:
autonumber_size = 5
autonumber_templ = u'%0' + str(autonumber_size) + u'd'
template_dict['autonumber'] = autonumber_templ % self._num_downloads
if template_dict['playlist_index'] is not None:
template_dict['playlist_index'] = u'%05d' % template_dict['playlist_index']
sanitize = lambda k,v: sanitize_filename(
u'NA' if v is None else compat_str(v),
@ -373,10 +411,10 @@ class FileDownloader(object):
filename = self.params['outtmpl'] % template_dict
return filename
except KeyError as err:
self.trouble(u'ERROR: Erroneous output template')
self.report_error(u'Erroneous output template')
return None
except ValueError as err:
self.trouble(u'ERROR: Insufficient system charset ' + repr(preferredencoding()))
self.report_error(u'Insufficient system charset ' + repr(preferredencoding()))
return None
def _match_entry(self, info_dict):
@ -391,10 +429,144 @@ class FileDownloader(object):
if rejecttitle:
if re.search(rejecttitle, title, re.IGNORECASE):
return u'"' + title + '" title matched reject pattern "' + rejecttitle + '"'
date = info_dict.get('upload_date', None)
if date is not None:
dateRange = self.params.get('daterange', DateRange())
if date not in dateRange:
return u'[download] %s upload date is not in range %s' % (date_from_str(date).isoformat(), dateRange)
return None
def extract_info(self, url, download=True, ie_key=None, extra_info={}):
'''
Returns a list with a dictionary for each video we find.
If 'download', also downloads the videos.
extra_info is a dict containing the extra values to add to each result
'''
if ie_key:
ie = get_info_extractor(ie_key)()
ie.set_downloader(self)
ies = [ie]
else:
ies = self._ies
for ie in ies:
if not ie.suitable(url):
continue
if not ie.working():
self.report_warning(u'The program functionality for this site has been marked as broken, '
u'and will probably not work.')
try:
ie_result = ie.extract(url)
if ie_result is None: # Finished already (backwards compatibility; listformats and friends should be moved here)
break
if isinstance(ie_result, list):
# Backwards compatibility: old IE result format
for result in ie_result:
result.update(extra_info)
ie_result = {
'_type': 'compat_list',
'entries': ie_result,
}
else:
ie_result.update(extra_info)
if 'extractor' not in ie_result:
ie_result['extractor'] = ie.IE_NAME
return self.process_ie_result(ie_result, download=download)
except ExtractorError as de: # An error we somewhat expected
self.report_error(compat_str(de), de.format_traceback())
break
except Exception as e:
if self.params.get('ignoreerrors', False):
self.report_error(compat_str(e), tb=compat_str(traceback.format_exc()))
break
else:
raise
else:
self.report_error(u'no suitable InfoExtractor: %s' % url)
def process_ie_result(self, ie_result, download=True, extra_info={}):
"""
Take the result of the ie(may be modified) and resolve all unresolved
references (URLs, playlist items).
It will also download the videos if 'download'.
Returns the resolved ie_result.
"""
result_type = ie_result.get('_type', 'video') # If not given we suppose it's a video, support the default old system
if result_type == 'video':
if 'playlist' not in ie_result:
# It isn't part of a playlist
ie_result['playlist'] = None
ie_result['playlist_index'] = None
if download:
self.process_info(ie_result)
return ie_result
elif result_type == 'url':
# We have to add extra_info to the results because it may be
# contained in a playlist
return self.extract_info(ie_result['url'],
download,
ie_key=ie_result.get('ie_key'),
extra_info=extra_info)
elif result_type == 'playlist':
# We process each entry in the playlist
playlist = ie_result.get('title', None) or ie_result.get('id', None)
self.to_screen(u'[download] Downloading playlist: %s' % playlist)
playlist_results = []
n_all_entries = len(ie_result['entries'])
playliststart = self.params.get('playliststart', 1) - 1
playlistend = self.params.get('playlistend', -1)
if playlistend == -1:
entries = ie_result['entries'][playliststart:]
else:
entries = ie_result['entries'][playliststart:playlistend]
n_entries = len(entries)
self.to_screen(u"[%s] playlist '%s': Collected %d video ids (downloading %d of them)" %
(ie_result['extractor'], playlist, n_all_entries, n_entries))
for i,entry in enumerate(entries,1):
self.to_screen(u'[download] Downloading video #%s of %s' %(i, n_entries))
extra = {
'playlist': playlist,
'playlist_index': i + playliststart,
}
entry_result = self.process_ie_result(entry,
download=download,
extra_info=extra)
playlist_results.append(entry_result)
ie_result['entries'] = playlist_results
return ie_result
elif result_type == 'compat_list':
def _fixup(r):
r.setdefault('extractor', ie_result['extractor'])
return r
ie_result['entries'] = [
self.process_ie_result(_fixup(r), download=download)
for r in ie_result['entries']
]
return ie_result
else:
raise Exception('Invalid result type: %s' % result_type)
def process_info(self, info_dict):
"""Process a single dictionary returned by an InfoExtractor."""
"""Process a single resolved IE result."""
assert info_dict.get('_type', 'video') == 'video'
#We increment the download the download count here to match the previous behaviour.
self.increment_downloads()
info_dict['fulltitle'] = info_dict['title']
if len(info_dict['title']) > 200:
info_dict['title'] = info_dict['title'][:197] + u'...'
# Keep for backwards compatibility
info_dict['stitle'] = info_dict['title']
@ -417,6 +589,8 @@ class FileDownloader(object):
# Forced printings
if self.params.get('forcetitle', False):
compat_print(info_dict['title'])
if self.params.get('forceid', False):
compat_print(info_dict['id'])
if self.params.get('forceurl', False):
compat_print(info_dict['url'])
if self.params.get('forcethumbnail', False) and 'thumbnail' in info_dict:
@ -437,10 +611,10 @@ class FileDownloader(object):
try:
dn = os.path.dirname(encodeFilename(filename))
if dn != '' and not os.path.exists(dn): # dn is already encoded
if dn != '' and not os.path.exists(dn):
os.makedirs(dn)
except (OSError, IOError) as err:
self.trouble(u'ERROR: unable to create directory ' + compat_str(err))
self.report_error(u'unable to create directory ' + compat_str(err))
return
if self.params.get('writedescription', False):
@ -450,20 +624,43 @@ class FileDownloader(object):
with io.open(encodeFilename(descfn), 'w', encoding='utf-8') as descfile:
descfile.write(info_dict['description'])
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write description file ' + descfn)
self.report_error(u'Cannot write description file ' + descfn)
return
if self.params.get('writesubtitles', False) 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
try:
srtfn = filename.rsplit('.', 1)[0] + u'.srt'
self.report_writesubtitles(srtfn)
with io.open(encodeFilename(srtfn), 'w', encoding='utf-8') as srtfile:
srtfile.write(info_dict['subtitles'])
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write subtitles file ' + descfn)
return
subtitle = info_dict['subtitles'][0]
(sub_error, sub_lang, sub) = subtitle
sub_format = self.params.get('subtitlesformat')
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('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'
@ -472,9 +669,23 @@ class FileDownloader(object):
json_info_dict = dict((k, v) for k,v in info_dict.items() if not k in ['urlhandle'])
write_json_file(json_info_dict, encodeFilename(infofn))
except (OSError, IOError):
self.trouble(u'ERROR: Cannot write metadata to JSON file ' + infofn)
self.report_error(u'Cannot write metadata to JSON file ' + infofn)
return
if self.params.get('writethumbnail', False):
if 'thumbnail' in info_dict:
thumb_format = info_dict['thumbnail'].rpartition(u'/')[2].rpartition(u'.')[2]
if not thumb_format:
thumb_format = 'jpg'
thumb_filename = filename.rpartition('.')[0] + u'.' + thumb_format
self.to_screen(u'[%s] %s: Downloading thumbnail ...' %
(info_dict['extractor'], info_dict['id']))
uf = compat_urllib_request.urlopen(info_dict['thumbnail'])
with open(thumb_filename, 'wb') as thumbf:
shutil.copyfileobj(uf, thumbf)
self.to_screen(u'[%s] %s: Writing thumbnail to: %s' %
(info_dict['extractor'], info_dict['id'], thumb_filename))
if not self.params.get('skip_download', False):
if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(filename)):
success = True
@ -484,17 +695,17 @@ class FileDownloader(object):
except (OSError, IOError) as err:
raise UnavailableVideoError()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
self.trouble(u'ERROR: unable to download video data: %s' % str(err))
self.report_error(u'unable to download video data: %s' % str(err))
return
except (ContentTooShortError, ) as err:
self.trouble(u'ERROR: content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
self.report_error(u'content too short (expected %s bytes and served %s)' % (err.expected, err.downloaded))
return
if success:
try:
self.post_process(filename, info_dict)
except (PostProcessingError) as err:
self.trouble(u'ERROR: postprocessing: %s' % str(err))
self.report_error(u'postprocessing: %s' % str(err))
return
def download(self, url_list):
@ -503,49 +714,14 @@ class FileDownloader(object):
raise SameFileError(self.params['outtmpl'])
for url in url_list:
suitable_found = False
for ie in self._ies:
# Go to next InfoExtractor if not suitable
if not ie.suitable(url):
continue
# Warn if the _WORKING attribute is False
if not ie.working():
self.report_warning(u'the program functionality for this site has been marked as broken, '
u'and will probably not work. If you want to go on, use the -i option.')
# Suitable InfoExtractor found
suitable_found = True
# Extract information from URL and process it
try:
videos = ie.extract(url)
except ExtractorError as de: # An error we somewhat expected
self.trouble(u'ERROR: ' + compat_str(de), de.format_traceback())
break
except Exception as e:
if self.params.get('ignoreerrors', False):
self.trouble(u'ERROR: ' + compat_str(e), tb=compat_str(traceback.format_exc()))
break
else:
raise
if len(videos or []) > 1 and self.fixed_template():
raise SameFileError(self.params['outtmpl'])
for video in videos or []:
video['extractor'] = ie.IE_NAME
try:
self.increment_downloads()
self.process_info(video)
except UnavailableVideoError:
self.trouble(u'\nERROR: unable to download video')
# Suitable InfoExtractor had been found; go to next URL
break
if not suitable_found:
self.trouble(u'ERROR: no suitable InfoExtractor: %s' % url)
try:
#It also downloads the videos
videos = self.extract_info(url)
except UnavailableVideoError:
self.report_error(u'unable to download video')
except MaxDownloadsReached:
self.to_screen(u'[info] Maximum number of downloaded files reached.')
raise
return self._download_retcode
@ -572,7 +748,7 @@ class FileDownloader(object):
except (IOError, OSError):
self.report_warning(u'Unable to remove downloaded video file')
def _download_with_rtmpdump(self, filename, url, player_url, page_url):
def _download_with_rtmpdump(self, filename, url, player_url, page_url, play_path, tc_url):
self.report_destination(filename)
tmpfilename = self.temp_name(filename)
@ -580,17 +756,22 @@ class FileDownloader(object):
try:
subprocess.call(['rtmpdump', '-h'], stdout=(open(os.path.devnull, 'w')), stderr=subprocess.STDOUT)
except (OSError, IOError):
self.trouble(u'ERROR: RTMP download detected but "rtmpdump" could not be run')
self.report_error(u'RTMP download detected but "rtmpdump" could not be run')
return False
# Download using rtmpdump. rtmpdump returns exit code 2 when
# the connection was interrumpted and resuming appears to be
# possible. This is part of rtmpdump's normal usage, AFAIK.
basic_args = ['rtmpdump', '-q', '-r', url, '-o', tmpfilename]
if self.params.get('verbose', False): basic_args[1] = '-v'
if player_url is not None:
basic_args += ['-W', player_url]
if page_url is not None:
basic_args += ['--pageUrl', page_url]
if play_path is not None:
basic_args += ['-y', play_path]
if tc_url is not None:
basic_args += ['--tcUrl', url]
args = basic_args + [[], ['-e', '-k', '1']][self.params.get('continuedl', False)]
if self.params.get('verbose', False):
try:
@ -625,7 +806,8 @@ class FileDownloader(object):
})
return True
else:
self.trouble(u'\nERROR: rtmpdump exited with code %d' % retval)
self.to_stderr(u"\n")
self.report_error(u'rtmpdump exited with code %d' % retval)
return False
# Keep a copy of the main cookiejar to pass to external downloaders
@ -701,7 +883,9 @@ class FileDownloader(object):
if url.startswith('rtmp'):
return self._download_with_rtmpdump(filename, url,
info_dict.get('player_url', None),
info_dict.get('page_url', None))
info_dict.get('page_url', None),
info_dict.get('play_path', None),
info_dict.get('tc_url', None))
tmpfilename = self.temp_name(filename)
stream = None
@ -784,7 +968,7 @@ class FileDownloader(object):
self.report_retry(count, retries)
if count > retries:
self.trouble(u'ERROR: giving up after %s retries' % retries)
self.report_error(u'giving up after %s retries' % retries)
return False
data_len = data.info().get('Content-length', None)
@ -820,12 +1004,13 @@ class FileDownloader(object):
filename = self.undo_temp_name(tmpfilename)
self.report_destination(filename)
except (OSError, IOError) as err:
self.trouble(u'ERROR: unable to open for writing: %s' % str(err))
self.report_error(u'unable to open for writing: %s' % str(err))
return False
try:
stream.write(data_block)
except (IOError, OSError) as err:
self.trouble(u'\nERROR: unable to write data: %s' % str(err))
self.to_stderr(u"\n")
self.report_error(u'unable to write data: %s' % str(err))
return False
if not self.params.get('noresizebuffer', False):
block_size = self.best_block_size(after - before, len(data_block))
@ -851,7 +1036,8 @@ class FileDownloader(object):
self.slow_down(start, byte_counter - resume_len)
if stream is None:
self.trouble(u'\nERROR: Did not get any data blocks')
self.to_stderr(u"\n")
self.report_error(u'Did not get any data blocks')
return False
stream.close()
self.report_finish()

2580
youtube_dl/InfoExtractors.py
View File

File diff suppressed because it is too large Load Diff

10
youtube_dl/PostProcessor.py
View File

@ -85,8 +85,9 @@ class FFmpegPostProcessor(PostProcessor):
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
stdout,stderr = p.communicate()
if p.returncode != 0:
stderr = stderr.decode('utf-8', 'replace')
msg = stderr.strip().split('\n')[-1]
raise FFmpegPostProcessorError(msg.decode('utf-8', 'replace'))
raise FFmpegPostProcessorError(msg)
def _ffmpeg_filename_argument(self, fn):
# ffmpeg broke --, see https://ffmpeg.org/trac/ffmpeg/ticket/2127 for details
@ -188,6 +189,11 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
prefix, sep, ext = path.rpartition(u'.') # not os.path.splitext, since the latter does not work on unicode in all setups
new_path = prefix + sep + extension
# If we download foo.mp3 and convert it to... foo.mp3, then don't delete foo.mp3, silly.
if new_path == path:
self._nopostoverwrites = True
try:
if self._nopostoverwrites and os.path.exists(encodeFilename(new_path)):
self._downloader.to_screen(u'[youtube] Post-process file %s exists, skipping' % new_path)
@ -210,7 +216,7 @@ class FFmpegExtractAudioPP(FFmpegPostProcessor):
self._downloader.to_stderr(u'WARNING: Cannot update utime of audio file')
information['filepath'] = new_path
return False,information
return self._nopostoverwrites,information
class FFmpegVideoConvertor(FFmpegPostProcessor):
def __init__(self, downloader=None,preferedformat=None):

145
youtube_dl/__init__.py
View File

@ -24,10 +24,15 @@ __authors__ = (
'Jaime Marquínez Ferrándiz',
'Jeff Crouse',
'Osama Khalid',
'Michael Walter',
'M. Yasoob Ullah Khalid',
'Julien Fraichard',
'Johny Mo Swag',
)
__license__ = 'Public Domain'
import codecs
import getpass
import optparse
import os
@ -46,7 +51,7 @@ from .FileDownloader import *
from .InfoExtractors import gen_extractors
from .PostProcessor import *
def parseOpts():
def parseOpts(overrideArguments=None):
def _readOptions(filename_bytes):
try:
optionf = open(filename_bytes)
@ -139,9 +144,14 @@ def parseOpts():
help='display the current browser identification', default=False)
general.add_option('--user-agent',
dest='user_agent', help='specify a custom user agent', metavar='UA')
general.add_option('--referer',
dest='referer', help='specify a custom referer, use if the video access is restricted to one domain',
metavar='REF', default=None)
general.add_option('--list-extractors',
action='store_true', dest='list_extractors',
help='List all supported extractors and the URLs they would handle', default=False)
general.add_option('--proxy', dest='proxy', default=None, help='Use the specified HTTP/HTTPS proxy', metavar='URL')
general.add_option('--no-check-certificate', action='store_true', dest='no_check_certificate', default=False, help='Suppress HTTPS certificate validation.')
general.add_option('--test', action='store_true', dest='test', default=False, help=optparse.SUPPRESS_HELP)
selection.add_option('--playlist-start',
@ -153,6 +163,9 @@ def parseOpts():
selection.add_option('--max-downloads', metavar='NUMBER', dest='max_downloads', help='Abort after downloading NUMBER files', default=None)
selection.add_option('--min-filesize', metavar='SIZE', dest='min_filesize', help="Do not download any videos smaller than SIZE (e.g. 50k or 44.6m)", default=None)
selection.add_option('--max-filesize', metavar='SIZE', dest='max_filesize', help="Do not download any videos larger than SIZE (e.g. 50k or 44.6m)", default=None)
selection.add_option('--date', metavar='DATE', dest='date', help='download only videos uploaded in this date', default=None)
selection.add_option('--datebefore', metavar='DATE', dest='datebefore', help='download only videos uploaded before this date', default=None)
selection.add_option('--dateafter', metavar='DATE', dest='dateafter', help='download only videos uploaded after this date', default=None)
authentication.add_option('-u', '--username',
@ -164,7 +177,8 @@ def parseOpts():
video_format.add_option('-f', '--format',
action='store', dest='format', metavar='FORMAT', help='video format code')
action='store', dest='format', metavar='FORMAT',
help='video format code, specifiy the order of preference using slashes: "-f 22/17/18"')
video_format.add_option('--all-formats',
action='store_const', dest='format', help='download all available video formats', const='all')
video_format.add_option('--prefer-free-formats',
@ -173,12 +187,24 @@ def parseOpts():
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-srt',
video_format.add_option('--write-sub', '--write-srt',
action='store_true', dest='writesubtitles',
help='write video closed captions to a .srt file (currently youtube only)', default=False)
video_format.add_option('--srt-lang',
help='write subtitle file (currently youtube only)', default=False)
video_format.add_option('--only-sub',
action='store_true', dest='skip_download',
help='[deprecated] alias of --skip-download', default=False)
video_format.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',
action='store_true', dest='listsubtitles',
help='lists all available subtitles for the video (currently youtube only)', default=False)
video_format.add_option('--sub-format',
action='store', dest='subtitlesformat', metavar='LANG',
help='subtitle format [srt/sbv] (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 closed captions to download (optional) use IETF language tags like \'en\'')
help='language of the subtitles to download (optional) use IETF language tags like \'en\'')
verbosity.add_option('-q', '--quiet',
action='store_true', dest='quiet', help='activates quiet mode', default=False)
@ -190,6 +216,8 @@ def parseOpts():
action='store_true', dest='geturl', help='simulate, quiet but print URL', default=False)
verbosity.add_option('-e', '--get-title',
action='store_true', dest='gettitle', help='simulate, quiet but print title', default=False)
verbosity.add_option('--get-id',
action='store_true', dest='getid', help='simulate, quiet but print id', default=False)
verbosity.add_option('--get-thumbnail',
action='store_true', dest='getthumbnail',
help='simulate, quiet but print thumbnail URL', default=False)
@ -211,18 +239,33 @@ def parseOpts():
help='display progress in console titlebar', default=False)
verbosity.add_option('-v', '--verbose',
action='store_true', dest='verbose', help='print various debugging information', default=False)
verbosity.add_option('--dump-intermediate-pages',
action='store_true', dest='dump_intermediate_pages', default=False,
help='print downloaded pages to debug problems(very verbose)')
filesystem.add_option('-t', '--title',
action='store_true', dest='usetitle', help='use title in file name', default=False)
action='store_true', dest='usetitle', help='use title in file name (default)', default=False)
filesystem.add_option('--id',
action='store_true', dest='useid', help='use video ID in file name', default=False)
action='store_true', dest='useid', help='use only video ID in file name', default=False)
filesystem.add_option('-l', '--literal',
action='store_true', dest='usetitle', help='[deprecated] alias of --title', default=False)
filesystem.add_option('-A', '--auto-number',
action='store_true', dest='autonumber',
help='number downloaded files starting from 00000', default=False)
filesystem.add_option('-o', '--output',
dest='outtmpl', metavar='TEMPLATE', help='output filename template. Use %(title)s to get the title, %(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, %(autonumber)s to get an automatically incremented number, %(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), %(extractor)s for the provider (youtube, metacafe, etc), %(id)s for the video id and %% for a literal percent. Use - to output to stdout. Can also be used to download to a different directory, for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .')
dest='outtmpl', metavar='TEMPLATE',
help=('output filename template. Use %(title)s to get the title, '
'%(uploader)s for the uploader name, %(uploader_id)s for the uploader nickname if different, '
'%(autonumber)s to get an automatically incremented number, '
'%(ext)s for the filename extension, %(upload_date)s for the upload date (YYYYMMDD), '
'%(extractor)s for the provider (youtube, metacafe, etc), '
'%(id)s for the video id , %(playlist)s for the playlist the video is in, '
'%(playlist_index)s for the position in the playlist and %% for a literal percent. '
'Use - to output to stdout. Can also be used to download to a different directory, '
'for example with -o \'/my/downloads/%(uploader)s/%(title)s-%(id)s.%(ext)s\' .'))
filesystem.add_option('--autonumber-size',
dest='autonumber_size', metavar='NUMBER',
help='Specifies the number of digits in %(autonumber)s when it is present in output filename template or --autonumber option is given')
filesystem.add_option('--restrict-filenames',
action='store_true', dest='restrictfilenames',
help='Restrict filenames to only ASCII characters, and avoid "&" and spaces in filenames', default=False)
@ -248,6 +291,9 @@ def parseOpts():
filesystem.add_option('--write-info-json',
action='store_true', dest='writeinfojson',
help='write video metadata to a .info.json file', default=False)
filesystem.add_option('--write-thumbnail',
action='store_true', dest='writethumbnail',
help='write thumbnail image to disk', default=False)
postproc.add_option('-x', '--extract-audio', action='store_true', dest='extractaudio', default=False,
@ -272,29 +318,38 @@ def parseOpts():
parser.add_option_group(authentication)
parser.add_option_group(postproc)
xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
if xdg_config_home:
userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
if overrideArguments is not None:
opts, args = parser.parse_args(overrideArguments)
if opts.verbose:
print(u'[debug] Override config: ' + repr(overrideArguments))
else:
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
systemConf = _readOptions('/etc/youtube-dl.conf')
userConf = _readOptions(userConfFile)
commandLineConf = sys.argv[1:]
argv = systemConf + userConf + commandLineConf
opts, args = parser.parse_args(argv)
if opts.verbose:
print(u'[debug] System config: ' + repr(systemConf))
print(u'[debug] User config: ' + repr(userConf))
print(u'[debug] Command-line args: ' + repr(commandLineConf))
xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
if xdg_config_home:
userConfFile = os.path.join(xdg_config_home, 'youtube-dl.conf')
else:
userConfFile = os.path.join(os.path.expanduser('~'), '.config', 'youtube-dl.conf')
systemConf = _readOptions('/etc/youtube-dl.conf')
userConf = _readOptions(userConfFile)
commandLineConf = sys.argv[1:]
argv = systemConf + userConf + commandLineConf
opts, args = parser.parse_args(argv)
if opts.verbose:
print(u'[debug] System config: ' + repr(systemConf))
print(u'[debug] User config: ' + repr(userConf))
print(u'[debug] Command-line args: ' + repr(commandLineConf))
return parser, opts, args
jar = None
def _real_main():
parser, opts, args = parseOpts()
def _real_main(argv=None):
# Compatibility fixes for Windows
if sys.platform == 'win32':
# https://github.com/rg3/youtube-dl/issues/820
codecs.register(lambda name: codecs.lookup('utf-8') if name == 'cp65001' else None)
parser, opts, args = parseOpts(argv)
global jar
# Open appropriate CookieJar
@ -313,6 +368,10 @@ def _real_main():
# 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
# Dump user agent
if opts.dump_user_agent:
@ -337,8 +396,16 @@ def _real_main():
# General configuration
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
if opts.proxy:
proxies = {'http': opts.proxy, 'https': opts.proxy}
else:
proxies = compat_urllib_request.getproxies()
# Set HTTPS proxy to HTTP one if given (https://github.com/rg3/youtube-dl/issues/805)
if 'http' in proxies and 'https' not in proxies:
proxies['https'] = proxies['http']
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())
compat_urllib_request.install_opener(opener)
socket.setdefaulttimeout(300) # 5 minutes should be enough (famous last words)
@ -411,6 +478,10 @@ def _real_main():
if opts.recodevideo is not None:
if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg']:
parser.error(u'invalid video recode format specified')
if opts.date is not None:
date = DateRange.day(opts.date)
else:
date = DateRange(opts.dateafter, opts.datebefore)
if sys.version_info < (3,):
# In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems)
@ -423,26 +494,28 @@ def _real_main():
or (opts.usetitle and u'%(title)s-%(id)s.%(ext)s')
or (opts.useid and u'%(id)s.%(ext)s')
or (opts.autonumber and u'%(autonumber)s-%(id)s.%(ext)s')
or u'%(id)s.%(ext)s')
or u'%(title)s-%(id)s.%(ext)s')
# File downloader
fd = FileDownloader({
'usenetrc': opts.usenetrc,
'username': opts.username,
'password': opts.password,
'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'forceurl': opts.geturl,
'forcetitle': opts.gettitle,
'forceid': opts.getid,
'forcethumbnail': opts.getthumbnail,
'forcedescription': opts.getdescription,
'forcefilename': opts.getfilename,
'forceformat': opts.getformat,
'simulate': opts.simulate,
'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'skip_download': (opts.skip_download or opts.simulate or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
'format': opts.format,
'format_limit': opts.format_limit,
'listformats': opts.listformats,
'outtmpl': outtmpl,
'autonumber_size': opts.autonumber_size,
'restrictfilenames': opts.restrictfilenames,
'ignoreerrors': opts.ignoreerrors,
'ratelimit': opts.ratelimit,
@ -461,17 +534,23 @@ def _real_main():
'updatetime': opts.updatetime,
'writedescription': opts.writedescription,
'writeinfojson': opts.writeinfojson,
'writethumbnail': opts.writethumbnail,
'writesubtitles': opts.writesubtitles,
'allsubtitles': opts.allsubtitles,
'listsubtitles': opts.listsubtitles,
'subtitlesformat': opts.subtitlesformat,
'subtitleslang': opts.subtitleslang,
'matchtitle': decodeOption(opts.matchtitle),
'rejecttitle': decodeOption(opts.rejecttitle),
'max_downloads': opts.max_downloads,
'prefer_free_formats': opts.prefer_free_formats,
'verbose': opts.verbose,
'dump_intermediate_pages': opts.dump_intermediate_pages,
'test': opts.test,
'keepvideo': opts.keepvideo,
'min_filesize': opts.min_filesize,
'max_filesize': opts.max_filesize
'max_filesize': opts.max_filesize,
'daterange': date,
})
if opts.verbose:
@ -523,9 +602,9 @@ def _real_main():
sys.exit(retcode)
def main():
def main(argv=None):
try:
_real_main()
_real_main(argv)
except DownloadError:
sys.exit(1)
except SameFileError:

3
youtube_dl/__main__.py
View File

@ -9,7 +9,8 @@ import sys
if __package__ is None and not hasattr(sys, "frozen"):
# direct call of __main__.py
import os.path
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
path = os.path.realpath(os.path.abspath(__file__))
sys.path.append(os.path.dirname(os.path.dirname(path)))
import youtube_dl

10
youtube_dl/update.py
View File

@ -37,7 +37,7 @@ def rsa_verify(message, signature, key):
def update_self(to_screen, verbose, filename):
"""Update the program file with the latest version from the repository"""
UPDATE_URL = "http://rg3.github.com/youtube-dl/update/"
UPDATE_URL = "http://rg3.github.io/youtube-dl/update/"
VERSION_URL = UPDATE_URL + 'LATEST_VERSION'
JSON_URL = UPDATE_URL + 'versions.json'
UPDATES_RSA_KEY = (0x9d60ee4d8f805312fdb15a62f87b95bd66177b91df176765d13514a0f1754bcd2057295c5b6f1d35daa6742c3ffc9a82d3e118861c207995a8031e151d863c9927e304576bc80692bc8e094896fcf11b66f3e29e04e3a71e9a11558558acea1840aec37fc396fb6b65dc81a1c4144e03bd1c011de62e3f1357b327d08426fe93, 65537)
@ -78,7 +78,7 @@ def update_self(to_screen, verbose, filename):
to_screen(u'Updating to version ' + versions_info['latest'] + '...')
version = versions_info['versions'][versions_info['latest']]
print_notes(versions_info['versions'])
print_notes(to_screen, versions_info['versions'])
if not os.access(filename, os.W_OK):
to_screen(u'ERROR: no write permissions on %s' % filename)
@ -157,11 +157,15 @@ del "%s"
to_screen(u'Updated youtube-dl. Restart youtube-dl to use the new version.')
def print_notes(versions, fromVersion=__version__):
def get_notes(versions, fromVersion):
notes = []
for v,vdata in sorted(versions.items()):
if v > fromVersion:
notes.extend(vdata.get('notes', []))
return notes
def print_notes(to_screen, versions, fromVersion=__version__):
notes = get_notes(versions, fromVersion)
if notes:
to_screen(u'PLEASE NOTE:')
for note in notes:

123
youtube_dl/utils.py
View File

@ -1,6 +1,7 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import errno
import gzip
import io
import json
@ -12,6 +13,7 @@ import traceback
import zlib
import email.utils
import json
import datetime
try:
import urllib.request as compat_urllib_request
@ -148,6 +150,10 @@ try:
except NameError:
compat_chr = chr
def compat_ord(c):
if type(c) is int: return c
else: return ord(c)
std_headers = {
'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) Gecko/20100101 Firefox/10.0',
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
@ -311,7 +317,7 @@ def clean_html(html):
html = re.sub('<.*?>', '', html)
# Replace html entities
html = unescapeHTML(html)
return html
return html.strip()
def sanitize_open(filename, open_mode):
@ -329,16 +335,24 @@ def sanitize_open(filename, open_mode):
if sys.platform == 'win32':
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
return (sys.stdout, filename)
return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename)
stream = open(encodeFilename(filename), open_mode)
return (stream, filename)
except (IOError, OSError) as err:
# In case of error, try to remove win32 forbidden chars
filename = re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', filename)
if err.errno in (errno.EACCES,):
raise
# An exception here should be caught in the caller
stream = open(encodeFilename(filename), open_mode)
return (stream, filename)
# In case of error, try to remove win32 forbidden chars
alt_filename = os.path.join(
re.sub(u'[/<>:"\\|\\\\?\\*]', u'#', path_part)
for path_part in os.path.split(filename)
)
if alt_filename == filename:
raise
else:
# An exception here should be caught in the caller
stream = open(encodeFilename(filename), open_mode)
return (stream, alt_filename)
def timeconvert(timestr):
@ -429,12 +443,35 @@ def decodeOption(optval):
assert isinstance(optval, compat_str)
return optval
def formatSeconds(secs):
if secs > 3600:
return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
elif secs > 60:
return '%d:%02d' % (secs // 60, secs % 60)
else:
return '%d' % secs
def make_HTTPS_handler(opts):
if sys.version_info < (3,2):
# Python's 2.x handler is very simplistic
return compat_urllib_request.HTTPSHandler()
else:
import ssl
context = ssl.SSLContext(ssl.PROTOCOL_SSLv23)
context.set_default_verify_paths()
context.verify_mode = (ssl.CERT_NONE
if opts.no_check_certificate
else ssl.CERT_REQUIRED)
return compat_urllib_request.HTTPSHandler(context=context)
class ExtractorError(Exception):
"""Error during info extraction."""
def __init__(self, msg, tb=None):
""" tb, if given, is the original traceback (so that it can be printed out). """
super(ExtractorError, self).__init__(msg)
self.traceback = tb
self.exc_info = sys.exc_info() # preserve original exception
def format_traceback(self):
if self.traceback is None:
@ -449,7 +486,10 @@ class DownloadError(Exception):
configured to continue on errors. They will contain the appropriate
error message.
"""
pass
def __init__(self, msg, exc_info=None):
""" exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
super(DownloadError, self).__init__(msg)
self.exc_info = exc_info
class SameFileError(Exception):
@ -564,3 +604,70 @@ class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
https_request = http_request
https_response = http_response
def unified_strdate(date_str):
"""Return a string with the date in the format YYYYMMDD"""
upload_date = None
#Replace commas
date_str = date_str.replace(',',' ')
# %z (UTC offset) is only supported in python>=3.2
date_str = re.sub(r' (\+|-)[\d]*$', '', date_str)
format_expressions = ['%d %B %Y', '%B %d %Y', '%b %d %Y', '%Y-%m-%d', '%d/%m/%Y', '%Y/%m/%d %H:%M:%S']
for expression in format_expressions:
try:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
except:
pass
return upload_date
def date_from_str(date_str):
"""
Return a datetime object from a string in the format YYYYMMDD or
(now|today)[+-][0-9](day|week|month|year)(s)?"""
today = datetime.date.today()
if date_str == 'now'or date_str == 'today':
return today
match = re.match('(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
if match is not None:
sign = match.group('sign')
time = int(match.group('time'))
if sign == '-':
time = -time
unit = match.group('unit')
#A bad aproximation?
if unit == 'month':
unit = 'day'
time *= 30
elif unit == 'year':
unit = 'day'
time *= 365
unit += 's'
delta = datetime.timedelta(**{unit: time})
return today + delta
return datetime.datetime.strptime(date_str, "%Y%m%d").date()
class DateRange(object):
"""Represents a time interval between two dates"""
def __init__(self, start=None, end=None):
"""start and end must be strings in the format accepted by date"""
if start is not None:
self.start = date_from_str(start)
else:
self.start = datetime.datetime.min.date()
if end is not None:
self.end = date_from_str(end)
else:
self.end = datetime.datetime.max.date()
if self.start > self.end:
raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
@classmethod
def day(cls, day):
"""Returns a range that only contains the given day"""
return cls(day,day)
def __contains__(self, date):
"""Check if the date is in the range"""
if not isinstance(date, datetime.date):
date = date_from_str(date)
return self.start <= date <= self.end
def __str__(self):
return '%s - %s' % ( self.start.isoformat(), self.end.isoformat())

2
youtube_dl/version.py
View File

@ -1,2 +1,2 @@
__version__ = '2013.02.25'
__version__ = '2013.05.14'