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
This commit is contained in:
Rogério Brito 2013-06-30 12:15:17 -03:00
commit 0f58da6725
78 changed files with 1402 additions and 947 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@ -116,12 +116,14 @@ which means you can modify it, redistribute it or use it however you like.
-F, --list-formats list all available formats (currently youtube
only)
--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)
--list-subs lists all available subtitles for the video
(currently youtube only)
--sub-format FORMAT subtitle format [srt/sbv] (default=srt)
--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'
@ -166,7 +168,7 @@ The `-o` option allows users to indicate a template for the output file names. T
- `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).
The current default template is `%(title)s-%(id)s.%(ext)s`.
In some cases, you don't want special characters such as 中, spaces, or &, such as when transferring the downloaded filename to a Windows system or the filename through an 8bit-unsafe channel. In these cases, add the `--restrict-filenames` flag to get a shorter title:

83
devscripts/youtube_genalgo.py Normal file
View File

@ -0,0 +1,83 @@
#!/usr/bin/env python
# Generate youtube signature algorithm from test cases
import sys
tests = [
# 88
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<",
"J:|}][{=+-_)(*&;%$#@>MNBVCXZASDFGH^KLPOIUYTREWQ0987654321mnbvcxzasdfghrklpoiuytej"),
# 87
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
"!?;:|}][{=+-_)(*&^$#@/MNBVCXZASqFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"),
# 86 - vfl_ymO4Z 2013/06/27
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
"ertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!/#$%^&*()_-+={[|};?@"),
# 85
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<",
"{>/?;}[.=+-_)(*&^%$#@!MqBVCXZASDFwHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"),
# 84
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
"<.>?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWe098765432rmnbvcxzasdfghjklpoiuyt1"),
# 83
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
"D.>/?;}[{=+_)(*&^%$#!MNBVCXeAS<FGHJKLPOIUYTREWZ0987654321mnbvcxzasdfghjklpoiuytrQ"),
# 82
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
"Q>/?;}[{=+-(*<^%$#@!MNBVCXZASDFGHKLPOIUY8REWT0q&7654321mnbvcxzasdfghjklpoiuytrew9"),
]
def find_matching(wrong, right):
idxs = [wrong.index(c) for c in right]
return compress(idxs)
return ('s[%d]' % i for i in idxs)
def compress(idxs):
def _genslice(start, end, step):
starts = '' if start == 0 else str(start)
ends = ':%d' % (end+step)
steps = '' if step == 1 else (':%d' % step)
return 's[%s%s%s]' % (starts, ends, steps)
step = None
for i, prev in zip(idxs[1:], idxs[:-1]):
if step is not None:
if i - prev == step:
continue
yield _genslice(start, prev, step)
step = None
continue
if i - prev in [-1, 1]:
step = i - prev
start = prev
continue
else:
yield 's[%d]' % prev
if step is None:
yield 's[%d]' % i
else:
yield _genslice(start, i, step)
def _assert_compress(inp, exp):
res = list(compress(inp))
if res != exp:
print('Got %r, expected %r' % (res, exp))
assert res == exp
_assert_compress([0,2,4,6], ['s[0]', 's[2]', 's[4]', 's[6]'])
_assert_compress([0,1,2,4,6,7], ['s[:3]', 's[4]', 's[6:8]'])
_assert_compress([8,0,1,2,4,7,6,9], ['s[8]', 's[:3]', 's[4]', 's[7:5:-1]', 's[9]'])
def gen(wrong, right, indent):
code = ' + '.join(find_matching(wrong, right))
return 'if len(s) == %d:\n%s return %s\n' % (len(wrong), indent, code)
def genall(tests):
indent = ' ' * 8
return indent + (indent + 'el').join(gen(wrong, right, indent) for wrong,right in tests)
def main():
print(genall(tests))
if __name__ == '__main__':
main()

44
test/helper.py Normal file
View File

@ -0,0 +1,44 @@
import io
import json
import os.path
import youtube_dl.extractor
from youtube_dl import YoutubeDL, YoutubeDLHandler
from youtube_dl.utils import (
compat_cookiejar,
compat_urllib_request,
)
# General configuration (from __init__, not very elegant...)
jar = compat_cookiejar.CookieJar()
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
parameters = json.load(pf)
class FakeYDL(YoutubeDL):
def __init__(self):
self.result = []
# Different instances of the downloader can't share the same dictionary
# some test set the "sublang" parameter, which would break the md5 checks.
self.params = dict(parameters)
def to_screen(self, s):
print(s)
def trouble(self, s, tb=None):
raise Exception(s)
def download(self, x):
self.result.append(x)
def get_testcases():
for ie in youtube_dl.extractor.gen_extractors():
t = getattr(ie, '_TEST', None)
if t:
t['name'] = type(ie).__name__[:-len('IE')]
yield t
for t in getattr(ie, '_TESTS', []):
t['name'] = type(ie).__name__[:-len('IE')]
yield t

14
test/test_all_urls.py
View File

@ -7,7 +7,8 @@ import unittest
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE, JustinTVIE
from youtube_dl.extractor import YoutubeIE, YoutubePlaylistIE, YoutubeChannelIE, JustinTVIE, gen_extractors
from helper import get_testcases
class TestAllURLsMatching(unittest.TestCase):
def test_youtube_playlist_matching(self):
@ -50,5 +51,16 @@ class TestAllURLsMatching(unittest.TestCase):
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')
def test_no_duplicates(self):
ies = gen_extractors()
for tc in get_testcases():
url = tc['url']
for ie in ies:
if type(ie).__name__ in ['GenericIE', tc['name'] + 'IE']:
self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
else:
self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
if __name__ == '__main__':
unittest.main()

27
test/test_download.py
View File

@ -14,10 +14,8 @@ import binascii
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import youtube_dl.YoutubeDL
import youtube_dl.extractor
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
@ -56,8 +54,9 @@ def _file_md5(fn):
with open(fn, 'rb') as f:
return hashlib.md5(f.read()).hexdigest()
with io.open(DEF_FILE, encoding='utf-8') as deff:
defs = json.load(deff)
from helper import get_testcases
defs = get_testcases()
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
parameters = json.load(pf)
@ -73,22 +72,23 @@ def generator(test_case):
def test_template(self):
ie = youtube_dl.extractor.get_info_extractor(test_case['name'])
def print_skipping(reason):
print('Skipping %s: %s' % (test_case['name'], reason))
if not ie._WORKING:
print('Skipping: IE marked as not _WORKING')
print_skipping('IE marked as not _WORKING')
return
if 'playlist' not in test_case and not test_case['file']:
print('Skipping: No output file specified')
print_skipping('No output file specified')
return
if 'skip' in test_case:
print('Skipping: {0}'.format(test_case['skip']))
print_skipping(test_case['skip'])
return
params = self.parameters.copy()
params.update(test_case.get('params', {}))
ydl = YoutubeDL(params)
for ie in youtube_dl.extractor.gen_extractors():
ydl.add_info_extractor(ie)
ydl.add_default_info_extractors()
finished_hook_called = set()
def _hook(status):
if status['status'] == 'finished':
@ -155,9 +155,12 @@ def generator(test_case):
### And add them to TestDownload
for n, test_case in enumerate(defs):
test_method = generator(test_case)
test_method.__name__ = "test_{0}".format(test_case["name"])
if getattr(TestDownload, test_method.__name__, False):
test_method.__name__ = "test_{0}_{1}".format(test_case["name"], n)
tname = 'test_' + str(test_case['name'])
i = 1
while hasattr(TestDownload, tname):
tname = 'test_' + str(test_case['name']) + '_' + str(i)
i += 1
test_method.__name__ = tname
setattr(TestDownload, test_method.__name__, test_method)
del test_method

24
test/test_youtube_lists.py
View File

@ -10,30 +10,8 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor import YoutubeUserIE, YoutubePlaylistIE, YoutubeIE, YoutubeChannelIE
from youtube_dl.utils import *
from youtube_dl import YoutubeDL
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
parameters = json.load(pf)
# General configuration (from __init__, not very elegant...)
jar = compat_cookiejar.CookieJar()
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
class FakeYDL(YoutubeDL):
def __init__(self):
self.result = []
self.params = parameters
def to_screen(self, s):
print(s)
def trouble(self, s, tb=None):
raise Exception(s)
def extract_info(self, url):
self.result.append(url)
return url
from helper import FakeYDL
class TestYoutubeLists(unittest.TestCase):
def assertIsPlaylist(self,info):

57
test/test_youtube_sig.py Executable file
View File

@ -0,0 +1,57 @@
#!/usr/bin/env python
import unittest
import sys
# Allow direct execution
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor.youtube import YoutubeIE
from helper import FakeYDL
sig = YoutubeIE(FakeYDL())._decrypt_signature
class TestYoutubeSig(unittest.TestCase):
def test_43_43(self):
wrong = '5AEEAE0EC39677BC65FD9021CCD115F1F2DBD5A59E4.C0B243A3E2DED6769199AF3461781E75122AE135135'
right = '931EA22157E1871643FA9519676DED253A342B0C.4E95A5DBD2F1F511DCC1209DF56CB77693CE0EAE'
self.assertEqual(sig(wrong), right)
def test_88(self):
wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<"
right = "J:|}][{=+-_)(*&;%$#@>MNBVCXZASDFGH^KLPOIUYTREWQ0987654321mnbvcxzasdfghrklpoiuytej"
self.assertEqual(sig(wrong), right)
def test_87(self):
wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<"
right = "!?;:|}][{=+-_)(*&^$#@/MNBVCXZASqFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"
self.assertEqual(sig(wrong), right)
def test_86(self):
wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<"
right = "ertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!/#$%^&*()_-+={[|};?@"
self.assertEqual(sig(wrong), right)
def test_85(self):
wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<"
right = "{>/?;}[.=+-_)(*&^%$#@!MqBVCXZASDFwHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"
self.assertEqual(sig(wrong), right)
def test_84(self):
wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<"
right = "<.>?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWe098765432rmnbvcxzasdfghjklpoiuyt1"
self.assertEqual(sig(wrong), right)
def test_83(self):
wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<"
right = "D.>/?;}[{=+_)(*&^%$#!MNBVCXeAS<FGHJKLPOIUYTREWZ0987654321mnbvcxzasdfghjklpoiuytrQ"
self.assertEqual(sig(wrong), right)
def test_82(self):
wrong = "qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<"
right = "Q>/?;}[{=+-(*<^%$#@!MNBVCXZASDFGHKLPOIUY8REWT0q&7654321mnbvcxzasdfghjklpoiuytrew9"
self.assertEqual(sig(wrong), right)
if __name__ == '__main__':
unittest.main()

36
test/test_youtube_subtitles.py
View File

@ -12,31 +12,7 @@ sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from youtube_dl.extractor import YoutubeIE
from youtube_dl.utils import *
from youtube_dl import YoutubeDL
PARAMETERS_FILE = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parameters.json")
with io.open(PARAMETERS_FILE, encoding='utf-8') as pf:
parameters = json.load(pf)
# General configuration (from __init__, not very elegant...)
jar = compat_cookiejar.CookieJar()
cookie_processor = compat_urllib_request.HTTPCookieProcessor(jar)
proxy_handler = compat_urllib_request.ProxyHandler()
opener = compat_urllib_request.build_opener(proxy_handler, cookie_processor, YoutubeDLHandler())
compat_urllib_request.install_opener(opener)
class FakeYDL(YoutubeDL):
def __init__(self):
self.result = []
# Different instances of the downloader can't share the same dictionary
# some test set the "sublang" parameter, which would break the md5 checks.
self.params = dict(parameters)
def to_screen(self, s):
print(s)
def trouble(self, s, tb=None):
raise Exception(s)
def download(self, x):
self.result.append(x)
from helper import FakeYDL
md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
@ -84,7 +60,7 @@ class TestYoutubeSubtitles(unittest.TestCase):
info_dict = IE.extract('QRS8MkLhQmM')
subtitles = info_dict[0]['subtitles']
self.assertEqual(len(subtitles), 13)
def test_youtube_subtitles_format(self):
def test_youtube_subtitles_sbv_format(self):
DL = FakeYDL()
DL.params['writesubtitles'] = True
DL.params['subtitlesformat'] = 'sbv'
@ -92,6 +68,14 @@ class TestYoutubeSubtitles(unittest.TestCase):
info_dict = IE.extract('QRS8MkLhQmM')
sub = info_dict[0]['subtitles'][0]
self.assertEqual(md5(sub[2]), '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')
def test_youtube_list_subtitles(self):
DL = FakeYDL()
DL.params['listsubtitles'] = True

699
test/tests.json
View File

@ -1,699 +0,0 @@
[
{
"name": "Youtube",
"url": "http://www.youtube.com/watch?v=BaW_jenozKc",
"file": "BaW_jenozKc.mp4",
"info_dict": {
"title": "youtube-dl test video \"'/\\ä↭𝕐",
"uploader": "Philipp Hagemeister",
"uploader_id": "phihag",
"upload_date": "20121002",
"description": "test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
}
},
{
"name": "Youtube",
"url": "http://www.youtube.com/watch?v=1ltcDfZMA3U",
"file": "1ltcDfZMA3U.flv",
"note": "Test VEVO video (#897)",
"info_dict": {
"upload_date": "20070518",
"title": "Maps - It Will Find You",
"description": "Music video by Maps performing It Will Find You.",
"uploader": "MuteUSA",
"uploader_id": "MuteUSA"
}
},
{
"name": "Youtube",
"url": "http://www.youtube.com/watch?v=UxxajLWwzqY",
"file": "UxxajLWwzqY.mp4",
"note": "Test generic use_cipher_signature video (#897)",
"info_dict": {
"upload_date": "20120506",
"title": "Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]",
"description": "md5:b085c9804f5ab69f4adea963a2dceb3c",
"uploader": "IconaPop",
"uploader_id": "IconaPop"
}
},
{
"name": "Dailymotion",
"md5": "392c4b85a60a90dc4792da41ce3144eb",
"url": "http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech",
"file": "x33vw9.mp4",
"info_dict": {
"uploader": "Alex and Van .",
"title": "Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
}
},
{
"name": "Metacafe",
"add_ie": ["Youtube"],
"url": "http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
"file": "_aUehQsCQtM.flv",
"info_dict": {
"upload_date": "20090102",
"title": "The Electric Company | \"Short I\" | PBS KIDS GO!",
"description": "md5:2439a8ef6d5a70e380c22f5ad323e5a8",
"uploader": "PBS",
"uploader_id": "PBS"
}
},
{
"name": "BlipTV",
"md5": "b2d849efcf7ee18917e4b4d9ff37cafe",
"url": "http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352",
"file": "5779306.m4v",
"info_dict": {
"upload_date": "20111205",
"description": "md5:9bc31f227219cde65e47eeec8d2dc596",
"uploader": "Comic Book Resources - CBR TV",
"title": "CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3"
}
},
{
"name": "XVideos",
"md5": "1d0c835822f0a71a7bf011855db929d0",
"url": "http://www.xvideos.com/video939581/funny_porns_by_s_-1",
"file": "939581.flv",
"info_dict": {
"title": "Funny Porns By >>>>S<<<<<< -1"
}
},
{
"name": "YouPorn",
"md5": "c37ddbaaa39058c76a7e86c6813423c1",
"url": "http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/",
"file": "505835.mp4",
"info_dict": {
"upload_date": "20101221",
"description": "Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
"uploader": "Ask Dan And Jennifer",
"title": "Sex Ed: Is It Safe To Masturbate Daily?"
}
},
{
"name": "Pornotube",
"md5": "374dd6dcedd24234453b295209aa69b6",
"url": "http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing",
"file": "1689755.flv",
"info_dict": {
"upload_date": "20090708",
"title": "Marilyn-Monroe-Bathing"
}
},
{
"name": "YouJizz",
"md5": "07e15fa469ba384c7693fd246905547c",
"url": "http://www.youjizz.com/videos/zeichentrick-1-2189178.html",
"file": "2189178.flv",
"info_dict": {
"title": "Zeichentrick 1"
}
},
{
"name": "Vimeo",
"md5": "8879b6cc097e987f02484baf890129e5",
"url": "http://vimeo.com/56015672",
"file": "56015672.mp4",
"info_dict": {
"title": "youtube-dl test video - ★ \" ' 幸 / \\ ä ↭ 𝕐",
"uploader": "Filippo Valsorda",
"uploader_id": "user7108434",
"upload_date": "20121220",
"description": "This is a test case for youtube-dl.\nFor more information, see github.com/rg3/youtube-dl\nTest chars: ★ \" ' 幸 / \\ ä ↭ 𝕐"
}
},
{
"name": "Soundcloud",
"md5": "ebef0a451b909710ed1d7787dddbf0d7",
"url": "http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy",
"file": "62986583.mp3",
"info_dict": {
"upload_date": "20121011",
"description": "No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
"uploader": "E.T. ExTerrestrial Music",
"title": "Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
}
},
{
"name": "StanfordOpenClassroom",
"md5": "544a9468546059d4e80d76265b0443b8",
"url": "http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100",
"file": "PracticalUnix_intro-environment.mp4",
"info_dict": {
"title": "Intro Environment"
}
},
{
"name": "XNXX",
"md5": "0831677e2b4761795f68d417e0b7b445",
"url": "http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_",
"file": "1135332.flv",
"info_dict": {
"title": "lida » Naked Funny Actress (5)"
}
},
{
"name": "Youku",
"url": "http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
"file": "XNDgyMDQ2NTQw_part00.flv",
"md5": "ffe3f2e435663dc2d1eea34faeff5b5b",
"params": { "test": false },
"info_dict": {
"title": "youtube-dl test video \"'/\\ä↭𝕐"
}
},
{
"name": "NBA",
"url": "http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html",
"file": "0021200253-okc-bkn-recap.nba.mp4",
"md5": "c0edcfc37607344e2ff8f13c378c88a4",
"info_dict": {
"description": "Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.",
"title": "Thunder vs. Nets"
}
},
{
"name": "JustinTV",
"url": "http://www.twitch.tv/thegamedevhub/b/296128360",
"file": "296128360.flv",
"md5": "ecaa8a790c22a40770901460af191c9a",
"info_dict": {
"upload_date": "20110927",
"uploader_id": 25114803,
"uploader": "thegamedevhub",
"title": "Beginner Series - Scripting With Python Pt.1"
}
},
{
"name": "MyVideo",
"url": "http://www.myvideo.de/watch/8229274/bowling_fail_or_win",
"file": "8229274.flv",
"md5": "2d2753e8130479ba2cb7e0a37002053e",
"info_dict": {
"title": "bowling-fail-or-win"
}
},
{
"name": "Escapist",
"url": "http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate",
"file": "6618-Breaking-Down-Baldurs-Gate.mp4",
"md5": "c6793dbda81388f4264c1ba18684a74d",
"info_dict": {
"description": "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
"uploader": "the-escapist-presents",
"title": "Breaking Down Baldur's Gate"
}
},
{
"name": "GooglePlus",
"url": "https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
"file": "ZButuJc6CtH.flv",
"info_dict": {
"upload_date": "20120613",
"uploader": "井上ヨシマサ",
"title": "嘆きの天使 降臨"
}
},
{
"name": "FunnyOrDie",
"url": "http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version",
"file": "0732f586d7.mp4",
"md5": "f647e9e90064b53b6e046e75d0241fbd",
"info_dict": {
"description": "Lyrics changed to match the video. Spoken cameo by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a concept by Dustin McLean (DustFilms.com). Performed, edited, and written by David A. Scott.",
"title": "Heart-Shaped Box: Literal Video Version"
}
},
{
"name": "Steam",
"url": "http://store.steampowered.com/video/105600/",
"playlist": [
{
"file": "81300.flv",
"md5": "f870007cee7065d7c76b88f0a45ecc07",
"info_dict": {
"title": "Terraria 1.1 Trailer"
}
},
{
"file": "80859.flv",
"md5": "61aaf31a5c5c3041afb58fb83cbb5751",
"info_dict": {
"title": "Terraria Trailer"
}
}
]
},
{
"name": "Ustream",
"url": "http://www.ustream.tv/recorded/20274954",
"file": "20274954.flv",
"md5": "088f151799e8f572f84eb62f17d73e5c",
"info_dict": {
"title": "Young Americans for Liberty February 7, 2012 2:28 AM",
"uploader": "Young Americans for Liberty"
}
},
{
"name": "InfoQ",
"url": "http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
"file": "12-jan-pythonthings.mp4",
"info_dict": {
"description": "Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
"title": "A Few of My Favorite [Python] Things"
},
"params": {
"skip_download": true
}
},
{
"name": "ComedyCentral",
"url": "http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart",
"file": "422212.mp4",
"md5": "4e2f5cb088a83cd8cdb7756132f9739d",
"info_dict": {
"upload_date": "20121214",
"description": "Kristen Stewart",
"uploader": "thedailyshow",
"title": "thedailyshow-kristen-stewart part 1"
}
},
{
"name": "RBMARadio",
"url": "http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011",
"file": "ford-lopatin-live-at-primavera-sound-2011.mp3",
"md5": "6bc6f9bcb18994b4c983bc3bf4384d95",
"info_dict": {
"title": "Live at Primavera Sound 2011",
"description": "Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
"uploader": "Ford & Lopatin",
"uploader_id": "ford-lopatin",
"location": "Spain"
}
},
{
"name": "Facebook",
"url": "https://www.facebook.com/photo.php?v=120708114770723",
"file": "120708114770723.mp4",
"md5": "48975a41ccc4b7a581abd68651c1a5a8",
"info_dict": {
"title": "PEOPLE ARE AWESOME 2013",
"duration": 279
}
},
{
"name": "EightTracks",
"url": "http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
"playlist": [
{
"file": "11885610.m4a",
"md5": "96ce57f24389fc8734ce47f4c1abcc55",
"info_dict": {
"title": "youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885608.m4a",
"md5": "4ab26f05c1f7291ea460a3920be8021f",
"info_dict": {
"title": "youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885679.m4a",
"md5": "d30b5b5f74217410f4689605c35d1fd7",
"info_dict": {
"title": "youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885680.m4a",
"md5": "4eb0a669317cd725f6bbd336a29f923a",
"info_dict": {
"title": "youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885682.m4a",
"md5": "1893e872e263a2705558d1d319ad19e8",
"info_dict": {
"title": "PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885683.m4a",
"md5": "b673c46f47a216ab1741ae8836af5899",
"info_dict": {
"title": "PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885684.m4a",
"md5": "1d74534e95df54986da7f5abf7d842b7",
"info_dict": {
"title": "phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
},
{
"file": "11885685.m4a",
"md5": "f081f47af8f6ae782ed131d38b9cd1c0",
"info_dict": {
"title": "phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
"uploader_id": "ytdl"
}
}
]
},
{
"name": "Keek",
"url": "http://www.keek.com/ytdl/keeks/NODfbab",
"file": "NODfbab.mp4",
"md5": "9b0636f8c0f7614afa4ea5e4c6e57e83",
"info_dict": {
"uploader": "ytdl",
"title": "test chars: \"'/\\ä<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
}
},
{
"name": "TED",
"url": "http://www.ted.com/talks/dan_dennett_on_our_consciousness.html",
"file": "102.mp4",
"md5": "8cd9dfa41ee000ce658fd48fb5d89a61",
"info_dict": {
"title": "Dan Dennett: The illusion of consciousness",
"description": "md5:c6fa72e6eedbd938c9caf6b2702f5922"
}
},
{
"name": "MySpass",
"url": "http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/",
"file": "11741.mp4",
"md5": "0b49f4844a068f8b33f4b7c88405862b",
"info_dict": {
"description": "Wer kann in die Fußstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
"title": "Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2"
}
},
{
"name": "Generic",
"url": "http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html",
"file": "13601338388002.mp4",
"md5": "85b90ccc9d73b4acd9138d3af4c27f89",
"info_dict": {
"uploader": "www.hodiho.fr",
"title": "Régis plante sa Jeep"
}
},
{
"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://resigno.tumblr.com/post/53364321212/e-de-extrema-importancia-que-esse-video-seja",
"file": "53364321212.mp4",
"md5": "0716d3dd51baf68a28b40fdf1251494e",
"info_dict": {
"title": "Rafael Lemos | Tumblr"
}
},
{
"name": "SoundcloudSet",
"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
"playlist":[
{
"file":"30510138.mp3",
"md5":"f9136bf103901728f29e419d2c70f55d",
"info_dict": {
"upload_date": "20111213",
"description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
"uploader": "The Royal Concept",
"title": "D-D-Dance"
}
},
{
"file":"47127625.mp3",
"md5":"09b6758a018470570f8fd423c9453dd8",
"info_dict": {
"upload_date": "20120521",
"description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
"uploader": "The Royal Concept",
"title": "The Royal Concept - Gimme Twice"
}
},
{
"file":"47127627.mp3",
"md5":"154abd4e418cea19c3b901f1e1306d9c",
"info_dict": {
"upload_date": "20120521",
"uploader": "The Royal Concept",
"title": "Goldrushed"
}
},
{
"file":"47127629.mp3",
"md5":"2f5471edc79ad3f33a683153e96a79c1",
"info_dict": {
"upload_date": "20120521",
"description": "The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
"uploader": "The Royal Concept",
"title": "In the End"
}
},
{
"file":"47127631.mp3",
"md5":"f9ba87aa940af7213f98949254f1c6e2",
"info_dict": {
"upload_date": "20120521",
"description": "The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
"uploader": "The Royal Concept",
"title": "Knocked Up"
}
},
{
"file":"75206121.mp3",
"md5":"f9d1fe9406717e302980c30de4af9353",
"info_dict": {
"upload_date": "20130116",
"description": "The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central). \r\nAs a gift to our fans we would like to offer you a free download of the track! ",
"uploader": "The Royal Concept",
"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": {
"upload_date": "20130504",
"uploader": "rachaneronas",
"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/julian-smith-travis-legg-watch-214727115.html",
"file": "214727115.flv",
"md5": "2e717f169c1be93d84d3794a00d4a325",
"info_dict": {
"title": "Julian Smith & Travis Legg Watch Julian Smith"
},
"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."
}
},
{
"name": "XHamster",
"url": "http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html",
"file": "1509445.flv",
"md5": "9f48e0e8d58e3076bb236ff412ab62fa",
"info_dict": {
"upload_date": "20121014",
"uploader_id": "Ruseful2011",
"title": "FemaleAgent Shy beauty takes the bait"
}
},
{
"name": "Hypem",
"url": "http://hypem.com/track/1v6ga/BODYWORK+-+TAME",
"file": "1v6ga.mp3",
"md5": "b9cc91b5af8995e9f0c1cee04c575828",
"info_dict":{
"title":"Tame"
}
},
{
"name": "Vbox7",
"url": "http://vbox7.com/play:249bb972c2",
"file": "249bb972c2.flv",
"md5": "9c70d6d956f888bdc08c124acc120cfe",
"info_dict":{
"title":"Смях! Чудо - чист за секунди - Скрита камера"
}
},
{
"name": "Gametrailers",
"url": "http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer",
"file": "zbvr8i.flv",
"md5": "c3edbc995ab4081976e16779bd96a878",
"info_dict": {
"title": "E3 2013: Debut Trailer"
},
"skip": "Requires rtmpdump"
},
{
"name": "Statigram",
"url": "http://statigr.am/p/484091715184808010_284179915",
"file": "484091715184808010_284179915.mp4",
"md5": "deda4ff333abe2e118740321e992605b",
"info_dict": {
"uploader_id": "videoseconds",
"title": "Instagram photo by @videoseconds (Videos)"
}
},
{
"name": "Break",
"url": "http://www.break.com/video/when-girls-act-like-guys-2468056",
"file": "2468056.mp4",
"md5": "a3513fb1547fba4fb6cfac1bffc6c46b",
"info_dict": {
"title": "When Girls Act Like D-Bags"
}
},
{
"name": "Vevo",
"url": "http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280",
"file": "GB1101300280.mp4",
"md5": "06bea460acb744eab74a9d7dcb4bfd61",
"info_dict": {
"title": "Somebody To Die For",
"upload_date": "20130624",
"uploader": "Hurts"
}
},
{
"name": "Tudou",
"url": "http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html",
"file": "159447792.f4v",
"md5": "ad7c358a01541e926a1e413612c6b10a",
"info_dict": {
"title": "卡马乔国足开大脚长传冲吊集锦"
}
}
]

2
youtube_dl/FileDownloader.py
View File

@ -137,7 +137,7 @@ class FileDownloader(object):
self.ydl.report_warning(*args, **kargs)
def report_error(self, *args, **kargs):
self.ydl.error(*args, **kargs)
self.ydl.report_error(*args, **kargs)
def slow_down(self, start_time, byte_counter):
"""Sleep if the download speed is over the rate limit."""

11
youtube_dl/YoutubeDL.py
View File

@ -13,7 +13,7 @@ import time
import traceback
from .utils import *
from .extractor import get_info_extractor
from .extractor import get_info_extractor, gen_extractors
from .FileDownloader import FileDownloader
@ -75,7 +75,7 @@ class YoutubeDL(object):
writeautomaticsub: Write the automatic 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)
subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt)
subtitleslang: Language 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.
@ -113,6 +113,13 @@ class YoutubeDL(object):
self._ies.append(ie)
ie.set_downloader(self)
def add_default_info_extractors(self):
"""
Add the InfoExtractors returned by gen_extractors to the end of the list
"""
for ie in gen_extractors():
self.add_info_extractor(ie)
def add_post_processor(self, pp):
"""Add a PostProcessor object to the end of the chain."""
self._pps.append(pp)

8
youtube_dl/__init__.py
View File

@ -26,7 +26,8 @@ __authors__ = (
'Julien Fraichard',
'Johny Mo Swag',
'Axel Noack',
)
'Albert Kim',
)
__license__ = 'Public Domain'
@ -205,7 +206,7 @@ def parseOpts(overrideArguments=None):
help='lists all available subtitles for the video (currently youtube only)', default=False)
video_format.add_option('--sub-format',
action='store', dest='subtitlesformat', metavar='FORMAT',
help='subtitle format [srt/sbv] (default=srt) (currently youtube only)', default='srt')
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\'')
@ -576,8 +577,7 @@ def _real_main(argv=None):
ydl.to_screen(u'[debug] Python version %s - %s' %(platform.python_version(), platform.platform()))
ydl.to_screen(u'[debug] Proxy map: ' + str(proxy_handler.proxies))
for extractor in extractors:
ydl.add_info_extractor(extractor)
ydl.add_default_info_extractors()
# PostProcessors
if opts.extractaudio:

86
youtube_dl/extractor/__init__.py
View File

@ -1,11 +1,13 @@
from .ard import ARDIE
from .arte import ArteTvIE
from .auengine import AUEngineIE
from .bandcamp import BandcampIE
from .bliptv import BlipTVIE, BlipTVUserIE
from .breakcom import BreakIE
from .collegehumor import CollegeHumorIE
from .comedycentral import ComedyCentralIE
from .cspan import CSpanIE
from .dailymotion import DailymotionIE
from .depositfiles import DepositFilesIE
from .eighttracks import EightTracksIE
@ -13,10 +15,12 @@ from .escapist import EscapistIE
from .facebook import FacebookIE
from .flickr import FlickrIE
from .funnyordie import FunnyOrDieIE
from .gamespot import GameSpotIE
from .gametrailers import GametrailersIE
from .generic import GenericIE
from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE
from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .hypem import HypemIE
from .ina import InaIE
@ -35,6 +39,7 @@ from .photobucket import PhotobucketIE
from .pornotube import PornotubeIE
from .rbmaradio import RBMARadioIE
from .redtube import RedTubeIE
from .ringtv import RingTVIE
from .soundcloud import SoundcloudIE, SoundcloudSetIE
from .spiegel import SpiegelIE
from .stanfordoc import StanfordOpenClassroomIE
@ -42,13 +47,17 @@ from .statigram import StatigramIE
from .steam import SteamIE
from .teamcoco import TeamcocoIE
from .ted import TEDIE
from .tf1 import TF1IE
from .tudou import TudouIE
from .tumblr import TumblrIE
from .tutv import TutvIE
from .ustream import UstreamIE
from .vbox7 import Vbox7IE
from .vevo import VevoIE
from .vimeo import VimeoIE
from .vine import VineIE
from .wat import WatIE
from .wimp import WimpIE
from .worldstarhiphop import WorldStarHipHopIE
from .xhamster import XHamsterIE
from .xnxx import XNXXIE
@ -61,79 +70,18 @@ from .youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserI
from .zdf import ZDFIE
_ALL_CLASSES = [
klass
for name, klass in globals().items()
if name.endswith('IE') and name != 'GenericIE'
]
_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 [
YoutubePlaylistIE(),
YoutubeChannelIE(),
YoutubeUserIE(),
YoutubeSearchIE(),
YoutubeIE(),
MetacafeIE(),
DailymotionIE(),
GoogleSearchIE(),
PhotobucketIE(),
YahooIE(),
YahooSearchIE(),
DepositFilesIE(),
FacebookIE(),
BlipTVIE(),
BlipTVUserIE(),
VimeoIE(),
MyVideoIE(),
ComedyCentralIE(),
EscapistIE(),
CollegeHumorIE(),
XVideosIE(),
SoundcloudSetIE(),
SoundcloudIE(),
InfoQIE(),
MixcloudIE(),
StanfordOpenClassroomIE(),
MTVIE(),
YoukuIE(),
XNXXIE(),
YouJizzIE(),
PornotubeIE(),
YouPornIE(),
GooglePlusIE(),
ArteTvIE(),
NBAIE(),
WorldStarHipHopIE(),
JustinTVIE(),
FunnyOrDieIE(),
SteamIE(),
UstreamIE(),
RBMARadioIE(),
EightTracksIE(),
KeekIE(),
TEDIE(),
MySpassIE(),
SpiegelIE(),
LiveLeakIE(),
ARDIE(),
ZDFIE(),
TumblrIE(),
BandcampIE(),
RedTubeIE(),
InaIE(),
HowcastIE(),
VineIE(),
FlickrIE(),
TeamcocoIE(),
XHamsterIE(),
HypemIE(),
Vbox7IE(),
GametrailersIE(),
StatigramIE(),
BreakIE(),
VevoIE(),
JukeboxIE(),
TudouIE(),
GenericIE()
]
return [klass() for klass in _ALL_CLASSES]
def get_info_extractor(ie_name):
"""Returns the info extractor class with the given ie_name"""

9
youtube_dl/extractor/ard.py
View File

@ -9,6 +9,15 @@ class ARDIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[^/\?]+)(?:\?.*)?'
_TITLE = r'<h1(?: class="boxTopHeadline")?>(?P<title>.*)</h1>'
_MEDIA_STREAM = r'mediaCollection\.addMediaStream\((?P<media_type>\d+), (?P<quality>\d+), "(?P<rtmp_url>[^"]*)", "(?P<video_url>[^"]*)", "[^"]*"\)'
_TEST = {
u'url': u'http://www.ardmediathek.de/das-erste/tagesschau-in-100-sek?documentId=14077640',
u'file': u'14077640.mp4',
u'md5': u'6ca8824255460c787376353f9e20bbd8',
u'info_dict': {
u"title": u"11.04.2013 09:23 Uhr - Tagesschau in 100 Sekunden"
},
u'skip': u'Requires rtmpdump'
}
def _real_extract(self, url):
# determine video id from url

124
youtube_dl/extractor/arte.py
View File

@ -1,53 +1,21 @@
import re
import socket
import json
from .common import InfoExtractor
from ..utils import (
compat_http_client,
compat_str,
compat_urllib_error,
# This is used by the not implemented extractLiveStream method
compat_urllib_parse,
compat_urllib_request,
ExtractorError,
unified_strdate,
)
class ArteTvIE(InfoExtractor):
"""arte.tv information extractor."""
_VALID_URL = r'(?:http://)?videos\.arte\.tv/(?:fr|de)/videos/.*'
_VALID_URL = r'(?:http://)?www\.arte.tv/guide/(?:fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
_LIVE_URL = r'index-[0-9]+\.html$'
IE_NAME = u'arte.tv'
def fetch_webpage(self, url):
request = compat_urllib_request.Request(url)
try:
self.report_download_webpage(url)
webpage = compat_urllib_request.urlopen(request).read()
except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err))
except ValueError as err:
raise ExtractorError(u'Invalid URL: %s' % url)
return webpage
def grep_webpage(self, url, regex, regexFlags, matchTuples):
page = self.fetch_webpage(url)
mobj = re.search(regex, page, regexFlags)
info = {}
if mobj is None:
raise ExtractorError(u'Invalid URL: %s' % url)
for (i, key, err) in matchTuples:
if mobj.group(i) is None:
raise ExtractorError(err)
else:
info[key] = mobj.group(i)
return info
# TODO implement Live Stream
# def extractLiveStream(self, url):
# video_lang = url.split('/')[-4]
@ -75,62 +43,44 @@ class ArteTvIE(InfoExtractor):
# )
# video_url = u'%s/%s' % (info.get('url'), info.get('path'))
def extractPlus7Stream(self, url):
video_lang = url.split('/')[-3]
info = self.grep_webpage(
url,
r'param name="movie".*?videorefFileUrl=(http[^\'"&]*)',
0,
[
(1, 'url', u'Invalid URL: %s' % url)
]
)
next_url = compat_urllib_parse.unquote(info.get('url'))
info = self.grep_webpage(
next_url,
r'<video lang="%s" ref="(http[^\'"&]*)' % video_lang,
0,
[
(1, 'url', u'Could not find <video> tag: %s' % url)
]
)
next_url = compat_urllib_parse.unquote(info.get('url'))
info = self.grep_webpage(
next_url,
r'<video id="(.*?)".*?>.*?' +
'<name>(.*?)</name>.*?' +
'<dateVideo>(.*?)</dateVideo>.*?' +
'<url quality="hd">(.*?)</url>',
re.DOTALL,
[
(1, 'id', u'could not extract video id: %s' % url),
(2, 'title', u'could not extract video title: %s' % url),
(3, 'date', u'could not extract video date: %s' % url),
(4, 'url', u'could not extract video url: %s' % url)
]
)
return {
'id': info.get('id'),
'url': compat_urllib_parse.unquote(info.get('url')),
'uploader': u'arte.tv',
'upload_date': unified_strdate(info.get('date')),
'title': info.get('title').decode('utf-8'),
'ext': u'mp4',
'format': u'NA',
'player_url': None,
}
def _real_extract(self, url):
video_id = url.split('/')[-1]
self.report_extraction(video_id)
mobj = re.match(self._VALID_URL, url)
name = mobj.group('name')
# This is not a real id, it can be for example AJT for the news
# http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
video_id = mobj.group('id')
if re.search(self._LIVE_URL, video_id) is not None:
raise ExtractorError(u'Arte live streams are not yet supported, sorry')
# self.extractLiveStream(url)
# return
else:
info = self.extractPlus7Stream(url)
return [info]
webpage = self._download_webpage(url, video_id)
json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
self.report_extraction(video_id)
info = json.loads(json_info)
player_info = info['videoJsonPlayer']
info_dict = {'id': player_info['VID'],
'title': player_info['VTI'],
'description': player_info['VDE'],
'upload_date': unified_strdate(player_info['VDA'].split(' ')[0]),
'thumbnail': player_info['programImage'],
}
formats = player_info['VSR'].values()
# We order the formats by quality
formats = sorted(formats, key=lambda f: int(f['height']))
# Pick the best quality
format_info = formats[-1]
if format_info['mediaType'] == u'rtmp':
info_dict['url'] = format_info['streamer']
info_dict['play_path'] = 'mp4:' + format_info['url']
info_dict['ext'] = 'mp4'
else:
info_dict['url'] = format_info['url']
info_dict['ext'] = 'mp4'
return info_dict

38
youtube_dl/extractor/auengine.py Normal file
View File

@ -0,0 +1,38 @@
import os.path
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
compat_urllib_parse_urlparse,
)
class AUEngineIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
webpage, u'title')
title = title.strip()
links = re.findall(r'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage)
links = [compat_urllib_parse.unquote(l) for l in links]
for link in links:
root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path)
if pathext == '.png':
thumbnail = link
elif pathext == '.mp4':
url = link
ext = pathext
if ext == title[-len(ext):]:
title = title[:-len(ext)]
ext = ext[1:]
return [{
'id': video_id,
'url': url,
'ext': ext,
'title': title,
'thumbnail': thumbnail,
}]

9
youtube_dl/extractor/bandcamp.py
View File

@ -9,6 +9,15 @@ from ..utils import (
class BandcampIE(InfoExtractor):
_VALID_URL = r'http://.*?\.bandcamp\.com/track/(?P<title>.*)'
_TEST = {
u'url': u'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
u'file': u'1812978515.mp3',
u'md5': u'cdeb30cdae1921719a3cbcab696ef53c',
u'info_dict': {
u"title": u"youtube-dl test song \"'/\\\u00e4\u21ad"
},
u'skip': u'There is a limit of 200 free downloads / month for the test song'
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

11
youtube_dl/extractor/bliptv.py
View File

@ -24,6 +24,17 @@ class BlipTVIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?blip\.tv/((.+/)|(play/)|(api\.swf#))(.+)$'
_URL_EXT = r'^.*\.([a-z0-9]+)$'
IE_NAME = u'blip.tv'
_TEST = {
u'url': u'http://blip.tv/cbr/cbr-exclusive-gotham-city-imposters-bats-vs-jokerz-short-3-5796352',
u'file': u'5779306.m4v',
u'md5': u'b2d849efcf7ee18917e4b4d9ff37cafe',
u'info_dict': {
u"upload_date": u"20111205",
u"description": u"md5:9bc31f227219cde65e47eeec8d2dc596",
u"uploader": u"Comic Book Resources - CBR TV",
u"title": u"CBR EXCLUSIVE: \"Gotham City Imposters\" Bats VS Jokerz Short 3"
}
}
def report_direct_download(self, title):
"""Report information extraction."""

8
youtube_dl/extractor/breakcom.py
View File

@ -5,6 +5,14 @@ from .common import InfoExtractor
class BreakIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
_TEST = {
u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
u'file': u'2468056.mp4',
u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
u'info_dict': {
u"title": u"When Girls Act Like D-Bags"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

13
youtube_dl/extractor/comedycentral.py
View File

@ -27,6 +27,17 @@ class ComedyCentralIE(InfoExtractor):
(the-colbert-report-(videos|collections)/(?P<clipID>[0-9]+)/[^/]*/(?P<cntitle>.*?))
|(watch/(?P<date>[^/]*)/(?P<tdstitle>.*)))))
$"""
_TEST = {
u'url': u'http://www.thedailyshow.com/watch/thu-december-13-2012/kristen-stewart',
u'file': u'422212.mp4',
u'md5': u'4e2f5cb088a83cd8cdb7756132f9739d',
u'info_dict': {
u"upload_date": u"20121214",
u"description": u"Kristen Stewart",
u"uploader": u"thedailyshow",
u"title": u"thedailyshow-kristen-stewart part 1"
}
}
_available_formats = ['3500', '2200', '1700', '1200', '750', '400']
@ -172,7 +183,7 @@ class ComedyCentralIE(InfoExtractor):
'ext': 'mp4',
'format': format,
'thumbnail': None,
'description': officialTitle,
'description': compat_str(officialTitle),
}
results.append(info)

1
youtube_dl/extractor/common.py
View File

@ -44,6 +44,7 @@ class InfoExtractor(object):
location: Physical location of the video.
player_url: SWF Player URL (used for rtmpdump).
subtitles: The subtitle file contents.
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

53
youtube_dl/extractor/cspan.py Normal file
View File

@ -0,0 +1,53 @@
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
)
class CSpanIE(InfoExtractor):
_VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
_TEST = {
u'url': u'http://www.c-spanvideo.org/program/HolderonV',
u'file': u'315139.flv',
u'md5': u'74a623266956f69e4df0068ab6c80fe4',
u'info_dict': {
u"title": u"Attorney General Eric Holder on Voting Rights Act Decision"
},
u'skip': u'Requires rtmpdump'
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
prog_name = mobj.group(1)
webpage = self._download_webpage(url, prog_name)
video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
data = compat_urllib_parse.urlencode({'programid': video_id,
'dynamic':'1'})
info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data
video_info = self._download_webpage(info_url, video_id, u'Downloading video info')
self.report_extraction(video_id)
title = self._html_search_regex(r'<string name="title">(.*?)</string>',
video_info, 'title')
description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"',
webpage, 'description',
flags=re.MULTILINE|re.DOTALL)
thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.*?)"',
webpage, 'thumbnail')
url = self._search_regex(r'<string name="URL">(.*?)</string>',
video_info, 'video url')
url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443')
path = self._search_regex(r'<string name="path">(.*?)</string>',
video_info, 'rtmp play path')
return {'id': video_id,
'title': title,
'ext': 'flv',
'url': url,
'play_path': path,
'description': description,
'thumbnail': thumbnail,
}

9
youtube_dl/extractor/dailymotion.py
View File

@ -14,6 +14,15 @@ class DailymotionIE(InfoExtractor):
_VALID_URL = r'(?i)(?:https?://)?(?:www\.)?dailymotion\.[a-z]{2,3}/video/([^/]+)'
IE_NAME = u'dailymotion'
_TEST = {
u'url': u'http://www.dailymotion.com/video/x33vw9_tutoriel-de-youtubeur-dl-des-video_tech',
u'file': u'x33vw9.mp4',
u'md5': u'392c4b85a60a90dc4792da41ce3144eb',
u'info_dict': {
u"uploader": u"Alex and Van .",
u"title": u"Tutoriel de Youtubeur\"DL DES VIDEO DE YOUTUBE\""
}
}
def _real_extract(self, url):
# Extract id and simplified title from URL

71
youtube_dl/extractor/eighttracks.py
View File

@ -12,6 +12,77 @@ from ..utils import (
class EightTracksIE(InfoExtractor):
IE_NAME = '8tracks'
_VALID_URL = r'https?://8tracks.com/(?P<user>[^/]+)/(?P<id>[^/#]+)(?:#.*)?$'
_TEST = {
u"name": u"EightTracks",
u"url": u"http://8tracks.com/ytdl/youtube-dl-test-tracks-a",
u"playlist": [
{
u"file": u"11885610.m4a",
u"md5": u"96ce57f24389fc8734ce47f4c1abcc55",
u"info_dict": {
u"title": u"youtue-dl project<>\"' - youtube-dl test track 1 \"'/\\\u00e4\u21ad",
u"uploader_id": u"ytdl"
}
},
{
u"file": u"11885608.m4a",
u"md5": u"4ab26f05c1f7291ea460a3920be8021f",
u"info_dict": {
u"title": u"youtube-dl project - youtube-dl test track 2 \"'/\\\u00e4\u21ad",
u"uploader_id": u"ytdl"
}
},
{
u"file": u"11885679.m4a",
u"md5": u"d30b5b5f74217410f4689605c35d1fd7",
u"info_dict": {
u"title": u"youtube-dl project as well - youtube-dl test track 3 \"'/\\\u00e4\u21ad",
u"uploader_id": u"ytdl"
}
},
{
u"file": u"11885680.m4a",
u"md5": u"4eb0a669317cd725f6bbd336a29f923a",
u"info_dict": {
u"title": u"youtube-dl project as well - youtube-dl test track 4 \"'/\\\u00e4\u21ad",
u"uploader_id": u"ytdl"
}
},
{
u"file": u"11885682.m4a",
u"md5": u"1893e872e263a2705558d1d319ad19e8",
u"info_dict": {
u"title": u"PH - youtube-dl test track 5 \"'/\\\u00e4\u21ad",
u"uploader_id": u"ytdl"
}
},
{
u"file": u"11885683.m4a",
u"md5": u"b673c46f47a216ab1741ae8836af5899",
u"info_dict": {
u"title": u"PH - youtube-dl test track 6 \"'/\\\u00e4\u21ad",
u"uploader_id": u"ytdl"
}
},
{
u"file": u"11885684.m4a",
u"md5": u"1d74534e95df54986da7f5abf7d842b7",
u"info_dict": {
u"title": u"phihag - youtube-dl test track 7 \"'/\\\u00e4\u21ad",
u"uploader_id": u"ytdl"
}
},
{
u"file": u"11885685.m4a",
u"md5": u"f081f47af8f6ae782ed131d38b9cd1c0",
u"info_dict": {
u"title": u"phihag - youtube-dl test track 8 \"'/\\\u00e4\u21ad",
u"uploader_id": u"ytdl"
}
}
]
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

10
youtube_dl/extractor/escapist.py
View File

@ -12,6 +12,16 @@ from ..utils import (
class EscapistIE(InfoExtractor):
_VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
_TEST = {
u'url': u'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
u'file': u'6618-Breaking-Down-Baldurs-Gate.mp4',
u'md5': u'c6793dbda81388f4264c1ba18684a74d',
u'info_dict': {
u"description": u"Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
u"uploader": u"the-escapist-presents",
u"title": u"Breaking Down Baldur's Gate"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

9
youtube_dl/extractor/facebook.py
View File

@ -22,6 +22,15 @@ class FacebookIE(InfoExtractor):
_LOGIN_URL = 'https://login.facebook.com/login.php?m&next=http%3A%2F%2Fm.facebook.com%2Fhome.php&'
_NETRC_MACHINE = 'facebook'
IE_NAME = u'facebook'
_TEST = {
u'url': u'https://www.facebook.com/photo.php?v=120708114770723',
u'file': u'120708114770723.mp4',
u'md5': u'48975a41ccc4b7a581abd68651c1a5a8',
u'info_dict': {
u"duration": 279,
u"title": u"PEOPLE ARE AWESOME 2013"
}
}
def report_login(self):
"""Report attempt to log in."""

10
youtube_dl/extractor/flickr.py
View File

@ -10,6 +10,16 @@ from ..utils import (
class FlickrIE(InfoExtractor):
"""Information Extractor for Flickr videos"""
_VALID_URL = r'(?:https?://)?(?:www\.)?flickr\.com/photos/(?P<uploader_id>[\w\-_@]+)/(?P<id>\d+).*'
_TEST = {
u'url': u'http://www.flickr.com/photos/forestwander-nature-pictures/5645318632/in/photostream/',
u'file': u'5645318632.mp4',
u'md5': u'6fdc01adbc89d72fc9c4f15b4a4ba87b',
u'info_dict': {
u"description": u"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.",
u"uploader_id": u"forestwander-nature-pictures",
u"title": u"Dark Hollow Waterfalls"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

9
youtube_dl/extractor/funnyordie.py
View File

@ -5,6 +5,15 @@ from .common import InfoExtractor
class FunnyOrDieIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?funnyordie\.com/videos/(?P<id>[0-9a-f]+)/.*$'
_TEST = {
u'url': u'http://www.funnyordie.com/videos/0732f586d7/heart-shaped-box-literal-video-version',
u'file': u'0732f586d7.mp4',
u'md5': u'f647e9e90064b53b6e046e75d0241fbd',
u'info_dict': {
u"description": u"Lyrics changed to match the video. Spoken cameo by Obscurus Lupa (from ThatGuyWithTheGlasses.com). Based on a concept by Dustin McLean (DustFilms.com). Performed, edited, and written by David A. Scott.",
u"title": u"Heart-Shaped Box: Literal Video Version"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

45
youtube_dl/extractor/gamespot.py Normal file
View File

@ -0,0 +1,45 @@
import re
import xml.etree.ElementTree
from .common import InfoExtractor
from ..utils import (
unified_strdate,
)
class GameSpotIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/([^/]+)/videos/([^/]+)-([^/d]+)/'
_TEST = {
u"url": u"http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/",
u"file": u"6410818.mp4",
u"md5": u"5569d64ca98db01f0177c934fe8c1e9b",
u"info_dict": {
u"title": u"Arma III - Community Guide: SITREP I",
u"upload_date": u"20130627",
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(3).split("-")[-1]
info_url = "http://www.gamespot.com/pages/video_player/xml.php?id="+str(video_id)
info_xml = self._download_webpage(info_url, video_id)
doc = xml.etree.ElementTree.fromstring(info_xml)
clip_el = doc.find('./playList/clip')
video_url = clip_el.find('./URI').text
title = clip_el.find('./title').text
ext = video_url.rpartition('.')[2]
thumbnail_url = clip_el.find('./screenGrabURI').text
view_count = int(clip_el.find('./views').text)
upload_date = unified_strdate(clip_el.find('./postDate').text)
return [{
'id' : video_id,
'url' : video_url,
'ext' : ext,
'title' : title,
'thumbnail' : thumbnail_url,
'upload_date' : upload_date,
'view_count' : view_count,
}]

9
youtube_dl/extractor/gametrailers.py
View File

@ -9,6 +9,15 @@ from ..utils import (
class GametrailersIE(InfoExtractor):
_VALID_URL = r'http://www.gametrailers.com/(?P<type>videos|reviews|full-episodes)/(?P<id>.*?)/(?P<title>.*)'
_TEST = {
u'url': u'http://www.gametrailers.com/videos/zbvr8i/mirror-s-edge-2-e3-2013--debut-trailer',
u'file': u'zbvr8i.flv',
u'md5': u'c3edbc995ab4081976e16779bd96a878',
u'info_dict': {
u"title": u"E3 2013: Debut Trailer"
},
u'skip': u'Requires rtmpdump'
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

13
youtube_dl/extractor/generic.py
View File

@ -15,6 +15,15 @@ class GenericIE(InfoExtractor):
_VALID_URL = r'.*'
IE_NAME = u'generic'
_TEST = {
u'url': u'http://www.hodiho.fr/2013/02/regis-plante-sa-jeep.html',
u'file': u'13601338388002.mp4',
u'md5': u'85b90ccc9d73b4acd9138d3af4c27f89',
u'info_dict': {
u"uploader": u"www.hodiho.fr",
u"title": u"R\u00e9gis plante sa Jeep"
}
}
def report_download_webpage(self, video_id):
"""Report webpage download."""
@ -102,7 +111,7 @@ class GenericIE(InfoExtractor):
mobj = re.search(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', webpage)
if mobj is None:
# Broaden the search a little bit: JWPlayer JS loader
mobj = re.search(r'[^A-Za-z0-9]?file:\s*["\'](http[^\'"&]*)', webpage)
mobj = re.search(r'[^A-Za-z0-9]?file["\']?:\s*["\'](http[^\'"&]*)', webpage)
if mobj is None:
# Try to find twitter cards info
mobj = re.search(r'<meta (?:property|name)="twitter:player:stream" (?:content|value)="(.+?)"', webpage)
@ -135,7 +144,7 @@ class GenericIE(InfoExtractor):
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
video_title = self._html_search_regex(r'<title>(.*)</title>',
webpage, u'video title')
webpage, u'video title', default=u'video')
# video uploader is domain name
video_uploader = self._search_regex(r'(?:https?://)?([^/]*)/.*',

11
youtube_dl/extractor/googleplus.py
View File

@ -1,3 +1,5 @@
# coding: utf-8
import datetime
import re
@ -12,6 +14,15 @@ class GooglePlusIE(InfoExtractor):
_VALID_URL = r'(?:https://)?plus\.google\.com/(?:[^/]+/)*?posts/(\w+)'
IE_NAME = u'plus.google'
_TEST = {
u"url": u"https://plus.google.com/u/0/108897254135232129896/posts/ZButuJc6CtH",
u"file": u"ZButuJc6CtH.flv",
u"info_dict": {
u"upload_date": u"20120613",
u"uploader": u"井上ヨシマサ",
u"title": u"嘆きの天使 降臨"
}
}
def _real_extract(self, url):
# Extract id from URL

48
youtube_dl/extractor/hotnewhiphop.py Normal file
View File

@ -0,0 +1,48 @@
import re
import base64
from .common import InfoExtractor
class HotNewHipHopIE(InfoExtractor):
_VALID_URL = r'http://www\.hotnewhiphop.com/.*\.(?P<id>.*)\.html'
_TEST = {
u'url': u"http://www.hotnewhiphop.com/freddie-gibbs-lay-it-down-song.1435540.html'",
u'file': u'1435540.mp3',
u'md5': u'2c2cd2f76ef11a9b3b581e8b232f3d96',
u'info_dict': {
u"title": u"Freddie Gibbs Songs - Lay It Down"
}
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
webpage_src = self._download_webpage(url, video_id)
video_url_base64 = self._search_regex(r'data-path="(.*?)"',
webpage_src, u'video URL', fatal=False)
if video_url_base64 == None:
video_url = self._search_regex(r'"contentUrl" content="(.*?)"', webpage_src,
u'video URL')
return self.url_result(video_url, ie='Youtube')
video_url = base64.b64decode(video_url_base64).decode('utf-8')
video_title = self._html_search_regex(r"<title>(.*)</title>",
webpage_src, u'title')
# Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
thumbnail = self._html_search_regex(r'"og:image" content="(.*)"',
webpage_src, u'thumbnail', fatal=False)
results = [{
'id': video_id,
'url' : video_url,
'title' : video_title,
'thumbnail' : thumbnail,
'ext' : 'mp3',
}]
return results

9
youtube_dl/extractor/howcast.py
View File

@ -5,6 +5,15 @@ from .common import InfoExtractor
class HowcastIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?howcast\.com/videos/(?P<id>\d+)'
_TEST = {
u'url': u'http://www.howcast.com/videos/390161-How-to-Tie-a-Square-Knot-Properly',
u'file': u'390161.mp4',
u'md5': u'1d7ba54e2c9d7dc6935ef39e00529138',
u'info_dict': {
u"description": u"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.",
u"title": u"How to Tie a Square Knot Properly"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

8
youtube_dl/extractor/hypem.py
View File

@ -15,6 +15,14 @@ from ..utils import (
class HypemIE(InfoExtractor):
"""Information Extractor for hypem"""
_VALID_URL = r'(?:http://)?(?:www\.)?hypem\.com/track/([^/]+)/([^/]+)'
_TEST = {
u'url': u'http://hypem.com/track/1v6ga/BODYWORK+-+TAME',
u'file': u'1v6ga.mp3',
u'md5': u'b9cc91b5af8995e9f0c1cee04c575828',
u'info_dict': {
u"title": u"Tame"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

8
youtube_dl/extractor/ina.py
View File

@ -6,6 +6,14 @@ from .common import InfoExtractor
class InaIE(InfoExtractor):
"""Information Extractor for Ina.fr"""
_VALID_URL = r'(?:http://)?(?:www\.)?ina\.fr/video/(?P<id>I[0-9]+)/.*'
_TEST = {
u'url': u'www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
u'file': u'I12055569.mp4',
u'md5': u'a667021bf2b41f8dc6049479d9bb38a3',
u'info_dict': {
u"title": u"Fran\u00e7ois Hollande \"Je crois que c'est clair\""
}
}
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)

12
youtube_dl/extractor/infoq.py
View File

@ -11,6 +11,18 @@ from ..utils import (
class InfoQIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
_TEST = {
u"name": u"InfoQ",
u"url": u"http://www.infoq.com/presentations/A-Few-of-My-Favorite-Python-Things",
u"file": u"12-jan-pythonthings.mp4",
u"info_dict": {
u"description": u"Mike Pirnat presents some tips and tricks, standard libraries and third party packages that make programming in Python a richer experience.",
u"title": u"A Few of My Favorite [Python] Things"
},
u"params": {
u"skip_download": True
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

11
youtube_dl/extractor/justintv.py
View File

@ -26,6 +26,17 @@ class JustinTVIE(InfoExtractor):
"""
_JUSTIN_PAGE_LIMIT = 100
IE_NAME = u'justin.tv'
_TEST = {
u'url': u'http://www.twitch.tv/thegamedevhub/b/296128360',
u'file': u'296128360.flv',
u'md5': u'ecaa8a790c22a40770901460af191c9a',
u'info_dict': {
u"upload_date": u"20110927",
u"uploader_id": 25114803,
u"uploader": u"thegamedevhub",
u"title": u"Beginner Series - Scripting With Python Pt.1"
}
}
def report_download_page(self, channel, offset):
"""Report attempt to download a single page of videos."""

9
youtube_dl/extractor/keek.py
View File

@ -6,6 +6,15 @@ from .common import InfoExtractor
class KeekIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?keek\.com/(?:!|\w+/keeks/)(?P<videoID>\w+)'
IE_NAME = u'keek'
_TEST = {
u'url': u'http://www.keek.com/ytdl/keeks/NODfbab',
u'file': u'NODfbab.mp4',
u'md5': u'9b0636f8c0f7614afa4ea5e4c6e57e83',
u'info_dict': {
u"uploader": u"ytdl",
u"title": u"test chars: \"'/\\\u00e4<>This is a test video for youtube-dl.For more information, contact phihag@phihag.de ."
}
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)

10
youtube_dl/extractor/liveleak.py
View File

@ -10,6 +10,16 @@ class LiveLeakIE(InfoExtractor):
_VALID_URL = r'^(?:http?://)?(?:\w+\.)?liveleak\.com/view\?(?:.*?)i=(?P<video_id>[\w_]+)(?:.*)'
IE_NAME = u'liveleak'
_TEST = {
u'url': u'http://www.liveleak.com/view?i=757_1364311680',
u'file': u'757_1364311680.mp4',
u'md5': u'0813c2430bea7a46bf13acf3406992f4',
u'info_dict': {
u"description": u"extremely bad day for this guy..!",
u"uploader": u"ljfriel2",
u"title": u"Most unlucky car accident"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

13
youtube_dl/extractor/metacafe.py
View File

@ -20,6 +20,19 @@ class MetacafeIE(InfoExtractor):
_DISCLAIMER = 'http://www.metacafe.com/family_filter/'
_FILTER_POST = 'http://www.metacafe.com/f/index.php?inputType=filter&controllerGroup=user'
IE_NAME = u'metacafe'
_TEST = {
u"add_ie": ["Youtube"],
u"url": u"http://metacafe.com/watch/yt-_aUehQsCQtM/the_electric_company_short_i_pbs_kids_go/",
u"file": u"_aUehQsCQtM.flv",
u"info_dict": {
u"upload_date": u"20090102",
u"title": u"The Electric Company | \"Short I\" | PBS KIDS GO!",
u"description": u"md5:2439a8ef6d5a70e380c22f5ad323e5a8",
u"uploader": u"PBS",
u"uploader_id": u"PBS"
}
}
def report_disclaimer(self):
"""Report disclaimer retrieval."""

9
youtube_dl/extractor/myspass.py
View File

@ -11,6 +11,15 @@ from ..utils import (
class MySpassIE(InfoExtractor):
_VALID_URL = r'http://www.myspass.de/.*'
_TEST = {
u'url': u'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
u'file': u'11741.mp4',
u'md5': u'0b49f4844a068f8b33f4b7c88405862b',
u'info_dict': {
u"description": u"Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?",
u"title": u"Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2"
}
}
def _real_extract(self, url):
META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'

8
youtube_dl/extractor/myvideo.py
View File

@ -18,6 +18,14 @@ class MyVideoIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?myvideo\.de/watch/([0-9]+)/([^?/]+).*'
IE_NAME = u'myvideo'
_TEST = {
u'url': u'http://www.myvideo.de/watch/8229274/bowling_fail_or_win',
u'file': u'8229274.flv',
u'md5': u'2d2753e8130479ba2cb7e0a37002053e',
u'info_dict': {
u"title": u"bowling-fail-or-win"
}
}
# Original Code from: https://github.com/dersphere/plugin.video.myvideo_de.git
# Released into the Public Domain by Tristan Fischer on 2013-05-19

9
youtube_dl/extractor/nba.py
View File

@ -8,6 +8,15 @@ from ..utils import (
class NBAIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:watch\.|www\.)?nba\.com/(?:nba/)?video(/[^?]*?)(?:/index\.html)?(?:\?.*)?$'
_TEST = {
u'url': u'http://www.nba.com/video/games/nets/2012/12/04/0021200253-okc-bkn-recap.nba/index.html',
u'file': u'0021200253-okc-bkn-recap.nba.mp4',
u'md5': u'c0edcfc37607344e2ff8f13c378c88a4',
u'info_dict': {
u"description": u"Kevin Durant scores 32 points and dishes out six assists as the Thunder beat the Nets in Brooklyn.",
u"title": u"Thunder vs. Nets"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

10
youtube_dl/extractor/photobucket.py
View File

@ -16,6 +16,16 @@ class PhotobucketIE(InfoExtractor):
# Check if it's necessary to keep the old extracion process
_VALID_URL = r'(?:http://)?(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
IE_NAME = u'photobucket'
_TEST = {
u'url': u'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
u'file': u'zpsc0c3b9fa.mp4',
u'md5': u'7dabfb92b0a31f6c16cebc0f8e60ff99',
u'info_dict': {
u"upload_date": u"20130504",
u"uploader": u"rachaneronas",
u"title": u"Tired of Link Building? Try BacklinkMyDomain.com!"
}
}
def _real_extract(self, url):
# Extract id from URL

9
youtube_dl/extractor/pornotube.py
View File

@ -10,6 +10,15 @@ from ..utils import (
class PornotubeIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
_TEST = {
u'url': u'http://pornotube.com/c/173/m/1689755/Marilyn-Monroe-Bathing',
u'file': u'1689755.flv',
u'md5': u'374dd6dcedd24234453b295209aa69b6',
u'info_dict': {
u"upload_date": u"20090708",
u"title": u"Marilyn-Monroe-Bathing"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

12
youtube_dl/extractor/rbmaradio.py
View File

@ -11,6 +11,18 @@ from ..utils import (
class RBMARadioIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?rbmaradio\.com/shows/(?P<videoID>[^/]+)$'
_TEST = {
u'url': u'http://www.rbmaradio.com/shows/ford-lopatin-live-at-primavera-sound-2011',
u'file': u'ford-lopatin-live-at-primavera-sound-2011.mp3',
u'md5': u'6bc6f9bcb18994b4c983bc3bf4384d95',
u'info_dict': {
u"uploader_id": u"ford-lopatin",
u"location": u"Spain",
u"description": u"Joel Ford and Daniel \u2019Oneohtrix Point Never\u2019 Lopatin fly their midified pop extravaganza to Spain. Live at Primavera Sound 2011.",
u"uploader": u"Ford & Lopatin",
u"title": u"Live at Primavera Sound 2011"
}
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)

8
youtube_dl/extractor/redtube.py
View File

@ -5,6 +5,14 @@ from .common import InfoExtractor
class RedTubeIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
_TEST = {
u'url': u'http://www.redtube.com/66418',
u'file': u'66418.mp4',
u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
u'info_dict': {
u"title": u"Sucked on a toilet"
}
}
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)

37
youtube_dl/extractor/ringtv.py Normal file
View File

@ -0,0 +1,37 @@
import re
from .common import InfoExtractor
class RingTVIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?ringtv\.craveonline\.com/videos/video/([^/]+)'
_TEST = {
u"url": u"http://ringtv.craveonline.com/videos/video/746619-canelo-alvarez-talks-about-mayweather-showdown",
u"file": u"746619.mp4",
u"md5": u"7c46b4057d22de32e0a539f017e64ad3",
u"info_dict": {
u"title": u"Canelo Alvarez talks about Mayweather showdown",
u"description": u"Saul \\\"Canelo\\\" Alvarez spoke to the media about his Sept. 14 showdown with Floyd Mayweather after their kick-off presser in NYC. Canelo is motivated and confident that he will have the speed and gameplan to beat the pound-for-pound king."
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1).split('-')[0]
webpage = self._download_webpage(url, video_id)
title = self._search_regex(r'<title>(.+?)</title>',
webpage, 'video title').replace(' | RingTV','')
description = self._search_regex(r'<div class="blurb">(.+?)</div>',
webpage, 'Description')
final_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/conversion/%s.mp4" %(str(video_id))
thumbnail_url = "http://ringtv.craveonline.springboardplatform.com/storage/ringtv.craveonline.com/snapshots/%s.jpg" %(str(video_id))
ext = final_url.split('.')[-1]
return [{
'id' : video_id,
'url' : final_url,
'ext' : ext,
'title' : title,
'thumbnail' : thumbnail_url,
'description' : description,
}]

79
youtube_dl/extractor/soundcloud.py
View File

@ -19,8 +19,19 @@ class SoundcloudIE(InfoExtractor):
of the stream token and uid
"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)'
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/([\w\d-]+)(?:[?].*)?$'
IE_NAME = u'soundcloud'
_TEST = {
u'url': u'http://soundcloud.com/ethmusic/lostin-powers-she-so-heavy',
u'file': u'62986583.mp3',
u'md5': u'ebef0a451b909710ed1d7787dddbf0d7',
u'info_dict': {
u"upload_date": u"20121011",
u"description": u"No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o'd",
u"uploader": u"E.T. ExTerrestrial Music",
u"title": u"Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1"
}
}
def report_resolve(self, video_id):
"""Report information extraction."""
@ -75,8 +86,72 @@ class SoundcloudSetIE(InfoExtractor):
of the stream token and uid
"""
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)'
_VALID_URL = r'^(?:https?://)?(?:www\.)?soundcloud\.com/([\w\d-]+)/sets/([\w\d-]+)(?:[?].*)?$'
IE_NAME = u'soundcloud:set'
_TEST = {
u"url":"https://soundcloud.com/the-concept-band/sets/the-royal-concept-ep",
u"playlist": [
{
u"file":"30510138.mp3",
u"md5":"f9136bf103901728f29e419d2c70f55d",
u"info_dict": {
u"upload_date": u"20111213",
u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
u"uploader": u"The Royal Concept",
u"title": u"D-D-Dance"
}
},
{
u"file":"47127625.mp3",
u"md5":"09b6758a018470570f8fd423c9453dd8",
u"info_dict": {
u"upload_date": u"20120521",
u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
u"uploader": u"The Royal Concept",
u"title": u"The Royal Concept - Gimme Twice"
}
},
{
u"file":"47127627.mp3",
u"md5":"154abd4e418cea19c3b901f1e1306d9c",
u"info_dict": {
u"upload_date": u"20120521",
u"uploader": u"The Royal Concept",
u"title": u"Goldrushed"
}
},
{
u"file":"47127629.mp3",
u"md5":"2f5471edc79ad3f33a683153e96a79c1",
u"info_dict": {
u"upload_date": u"20120521",
u"description": u"The Royal Concept from Stockholm\r\nFilip / Povel / David / Magnus\r\nwww.royalconceptband.com",
u"uploader": u"The Royal Concept",
u"title": u"In the End"
}
},
{
u"file":"47127631.mp3",
u"md5":"f9ba87aa940af7213f98949254f1c6e2",
u"info_dict": {
u"upload_date": u"20120521",
u"description": u"The Royal Concept from Stockholm\r\nFilip / David / Povel / Magnus\r\nwww.theroyalconceptband.com",
u"uploader": u"The Royal Concept",
u"title": u"Knocked Up"
}
},
{
u"file":"75206121.mp3",
u"md5":"f9d1fe9406717e302980c30de4af9353",
u"info_dict": {
u"upload_date": u"20130116",
u"description": u"The unreleased track World on Fire premiered on the CW's hit show Arrow (8pm/7pm central). \r\nAs a gift to our fans we would like to offer you a free download of the track! ",
u"uploader": u"The Royal Concept",
u"title": u"World On Fire"
}
}
]
}
def report_resolve(self, video_id):
"""Report information extraction."""

8
youtube_dl/extractor/spiegel.py
View File

@ -6,6 +6,14 @@ from .common import InfoExtractor
class SpiegelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spiegel\.de/video/[^/]*-(?P<videoID>[0-9]+)(?:\.html)?(?:#.*)?$'
_TEST = {
u'url': u'http://www.spiegel.de/video/vulkan-tungurahua-in-ecuador-ist-wieder-aktiv-video-1259285.html',
u'file': u'1259285.mp4',
u'md5': u'2c2754212136f35fb4b19767d242f66e',
u'info_dict': {
u"title": u"Vulkanausbruch in Ecuador: Der \"Feuerschlund\" ist wieder aktiv"
}
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)

8
youtube_dl/extractor/stanfordoc.py
View File

@ -20,6 +20,14 @@ class StanfordOpenClassroomIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?openclassroom.stanford.edu(?P<path>/?|(/MainFolder/(?:HomePage|CoursePage|VideoPage)\.php([?]course=(?P<course>[^&]+)(&video=(?P<video>[^&]+))?(&.*)?)?))$'
IE_NAME = u'stanfordoc'
_TEST = {
u'url': u'http://openclassroom.stanford.edu/MainFolder/VideoPage.php?course=PracticalUnix&video=intro-environment&speed=100',
u'file': u'PracticalUnix_intro-environment.mp4',
u'md5': u'544a9468546059d4e80d76265b0443b8',
u'info_dict': {
u"title": u"Intro Environment"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

9
youtube_dl/extractor/statigram.py
View File

@ -4,6 +4,15 @@ 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'info_dict': {
u"uploader_id": u"videoseconds",
u"title": u"Instagram photo by @videoseconds (Videos)"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

20
youtube_dl/extractor/steam.py
View File

@ -16,6 +16,26 @@ class SteamIE(InfoExtractor):
"""
_VIDEO_PAGE_TEMPLATE = 'http://store.steampowered.com/video/%s/'
_AGECHECK_TEMPLATE = 'http://store.steampowered.com/agecheck/video/%s/?snr=1_agecheck_agecheck__age-gate&ageDay=1&ageMonth=January&ageYear=1970'
_TEST = {
u"url": u"http://store.steampowered.com/video/105600/",
u"playlist": [
{
u"file": u"81300.flv",
u"md5": u"f870007cee7065d7c76b88f0a45ecc07",
u"info_dict": {
u"title": u"Terraria 1.1 Trailer"
}
},
{
u"file": u"80859.flv",
u"md5": u"61aaf31a5c5c3041afb58fb83cbb5751",
u"info_dict": {
u"title": u"Terraria Trailer"
}
}
]
}
@classmethod
def suitable(cls, url):

9
youtube_dl/extractor/teamcoco.py
View File

@ -8,6 +8,15 @@ from ..utils import (
class TeamcocoIE(InfoExtractor):
_VALID_URL = r'http://teamcoco\.com/video/(?P<url_title>.*)'
_TEST = {
u'url': u'http://teamcoco.com/video/louis-ck-interview-george-w-bush',
u'file': u'19705.mp4',
u'md5': u'27b6f7527da5acf534b15f21b032656e',
u'info_dict': {
u"description": u"Louis C.K. got starstruck by George W. Bush, so what? Part one.",
u"title": u"Louis C.K. Interview Pt. 1 11/3/11"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

9
youtube_dl/extractor/ted.py
View File

@ -14,6 +14,15 @@ class TEDIE(InfoExtractor):
(/lang/(.*?))? # The url may contain the language
/(?P<name>\w+) # Here goes the name and then ".html"
'''
_TEST = {
u'url': u'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html',
u'file': u'102.mp4',
u'md5': u'2d76ee1576672e0bd8f187513267adf6',
u'info_dict': {
u"description": u"md5:c6fa72e6eedbd938c9caf6b2702f5922",
u"title": u"Dan Dennett: The illusion of consciousness"
}
}
@classmethod
def suitable(cls, url):

35
youtube_dl/extractor/tf1.py Normal file
View File

@ -0,0 +1,35 @@
# coding: utf-8
import json
import re
from .common import InfoExtractor
class TF1IE(InfoExtractor):
"""
TF1 uses the wat.tv player, currently it can only download videos with the
html5 player enabled, it cannot download HD videos.
"""
_VALID_URL = r'http://videos.tf1.fr/.*-(.*?).html'
_TEST = {
u'url': u'http://videos.tf1.fr/auto-moto/citroen-grand-c4-picasso-2013-presentation-officielle-8062060.html',
u'file': u'10635995.mp4',
u'md5': u'66789d3e91278d332f75e1feb7aea327',
u'info_dict': {
u'title': u'Citroën Grand C4 Picasso 2013 : présentation officielle',
u'description': u'Vidéo officielle du nouveau Citroën Grand C4 Picasso, lancé à l\'automne 2013.',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
id = mobj.group(1)
webpage = self._download_webpage(url, id)
embed_url = self._html_search_regex(r'"(https://www.wat.tv/embedframe/.*?)"',
webpage, 'embed url')
embed_page = self._download_webpage(embed_url, id, u'Downloading embed player page')
wat_id = self._search_regex(r'UVID=(.*?)&', embed_page, 'wat id')
wat_info = self._download_webpage('http://www.wat.tv/interface/contentv3/%s' % wat_id, id, u'Downloading Wat info')
wat_info = json.loads(wat_info)['media']
wat_url = wat_info['url']
return self.url_result(wat_url, 'Wat')

8
youtube_dl/extractor/tudou.py
View File

@ -5,6 +5,14 @@ from .common import InfoExtractor
class TudouIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs)/(?:view|(.+?))/(?:([^/]+)|([^/]+)\.html)'
_TEST = {
u'url': u'http://www.tudou.com/listplay/zzdE77v6Mmo/2xN2duXMxmw.html',
u'file': u'159447792.f4v',
u'md5': u'ad7c358a01541e926a1e413612c6b10a',
u'info_dict': {
u"title": u"\u5361\u9a6c\u4e54\u56fd\u8db3\u5f00\u5927\u811a\u957f\u4f20\u51b2\u540a\u96c6\u9526"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

10
youtube_dl/extractor/tumblr.py
View File

@ -8,6 +8,14 @@ from ..utils import (
class TumblrIE(InfoExtractor):
_VALID_URL = r'http://(?P<blog_name>.*?)\.tumblr\.com/((post)|(video))/(?P<id>\d*)/(.*?)'
_TEST = {
u'url': u'http://resigno.tumblr.com/post/53364321212/e-de-extrema-importancia-que-esse-video-seja',
u'file': u'53364321212.mp4',
u'md5': u'0716d3dd51baf68a28b40fdf1251494e',
u'info_dict': {
u"title": u"Rafael Lemos"
}
}
def _real_extract(self, url):
m_url = re.match(self._VALID_URL, url)
@ -30,7 +38,7 @@ class TumblrIE(InfoExtractor):
# The only place where you can get a title, it's not complete,
# but searching in other places doesn't work for all videos
video_title = self._html_search_regex(r'<title>(?P<title>.*?)</title>',
video_title = self._html_search_regex(r'<title>(?P<title>.*?)(?: \| Tumblr)?</title>',
webpage, u'title', flags=re.DOTALL)
return [{'id': video_id,

41
youtube_dl/extractor/tutv.py Normal file
View File

@ -0,0 +1,41 @@
import base64
import re
from .common import InfoExtractor
from ..utils import (
compat_parse_qs,
)
class TutvIE(InfoExtractor):
_VALID_URL=r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
_TEST = {
u'url': u'http://tu.tv/videos/noah-en-pabellon-cuahutemoc',
u'file': u'2742556.flv',
u'md5': u'5eb766671f69b82e528dc1e7769c5cb2',
u'info_dict': {
u"title": u"Noah en pabellon cuahutemoc"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<meta property="og:title" content="(.*?)">', webpage, u'title')
internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, u'internal video ID')
data_url = u'http://tu.tv/flvurl.php?codVideo=' + str(internal_id)
data_content = self._download_webpage(data_url, video_id, note=u'Downloading video info')
data = compat_parse_qs(data_content)
video_url = base64.b64decode(data['kpt'][0]).decode('utf-8')
ext = video_url.partition(u'?')[0].rpartition(u'.')[2]
info = {
'id': internal_id,
'url': video_url,
'ext': ext,
'title': title,
}
return [info]

9
youtube_dl/extractor/ustream.py
View File

@ -6,6 +6,15 @@ from .common import InfoExtractor
class UstreamIE(InfoExtractor):
_VALID_URL = r'https?://www\.ustream\.tv/recorded/(?P<videoID>\d+)'
IE_NAME = u'ustream'
_TEST = {
u'url': u'http://www.ustream.tv/recorded/20274954',
u'file': u'20274954.flv',
u'md5': u'088f151799e8f572f84eb62f17d73e5c',
u'info_dict': {
u"uploader": u"Young Americans for Liberty",
u"title": u"Young Americans for Liberty February 7, 2012 2:28 AM"
}
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)

8
youtube_dl/extractor/vbox7.py
View File

@ -12,6 +12,14 @@ from ..utils import (
class Vbox7IE(InfoExtractor):
"""Information Extractor for Vbox7"""
_VALID_URL = r'(?:http://)?(?:www\.)?vbox7\.com/play:([^/]+)'
_TEST = {
u'url': u'http://vbox7.com/play:249bb972c2',
u'file': u'249bb972c2.flv',
u'md5': u'9c70d6d956f888bdc08c124acc120cfe',
u'info_dict': {
u"title": u"\u0421\u043c\u044f\u0445! \u0427\u0443\u0434\u043e - \u0447\u0438\u0441\u0442 \u0437\u0430 \u0441\u0435\u043a\u0443\u043d\u0434\u0438 - \u0421\u043a\u0440\u0438\u0442\u0430 \u043a\u0430\u043c\u0435\u0440\u0430"
}
}
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)

11
youtube_dl/extractor/vevo.py
View File

@ -3,7 +3,6 @@ import json
from .common import InfoExtractor
from ..utils import (
unified_strdate,
ExtractorError,
)
@ -13,6 +12,16 @@ class VevoIE(InfoExtractor):
(currently used by MTVIE)
"""
_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"title": u"Somebody To Die For"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

14
youtube_dl/extractor/vimeo.py
View File

@ -16,8 +16,20 @@ class VimeoIE(InfoExtractor):
"""Information extractor for vimeo.com."""
# _VALID_URL matches Vimeo URLs
_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]+)'
_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]+)(?:[?].*)?$'
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"
}
}
def _verify_video_password(self, url, video_id, webpage):
password = self._downloader.params.get('videopassword', None)

9
youtube_dl/extractor/vine.py
View File

@ -5,6 +5,15 @@ from .common import InfoExtractor
class VineIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:www\.)?vine\.co/v/(?P<id>\w+)'
_TEST = {
u'url': u'https://vine.co/v/b9KOOWX7HUx',
u'file': u'b9KOOWX7HUx.mp4',
u'md5': u'2f36fed6235b16da96ce9b4dc890940d',
u'info_dict': {
u"uploader": u"Jack Dorsey",
u"title": u"Chicken."
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

84
youtube_dl/extractor/wat.py Normal file
View File

@ -0,0 +1,84 @@
# coding: utf-8
import json
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
unified_strdate,
)
class WatIE(InfoExtractor):
_VALID_URL=r'http://www.wat.tv/.*-(?P<shortID>.*?)_.*?.html'
IE_NAME = 'wat.tv'
_TEST = {
u'url': u'http://www.wat.tv/video/world-war-philadelphia-vost-6bv55_2fjr7_.html',
u'file': u'10631273.mp4',
u'md5': u'0a4fe7870f31eaeabb5e25fd8da8414a',
u'info_dict': {
u'title': u'World War Z - Philadelphia VOST',
u'description': u'La menace est partout. Que se passe-t-il à Philadelphia ?\r\nWORLD WAR Z, avec Brad Pitt, au cinéma le 3 juillet.\r\nhttp://www.worldwarz.fr',
}
}
def download_video_info(self, real_id):
# 'contentv4' is used in the website, but it also returns the related
# videos, we don't need them
info = self._download_webpage('http://www.wat.tv/interface/contentv3/' + real_id, real_id, 'Downloading video info')
info = json.loads(info)
return info['media']
def _real_extract(self, url):
def real_id_for_chapter(chapter):
return chapter['tc_start'].split('-')[0]
mobj = re.match(self._VALID_URL, url)
short_id = mobj.group('shortID')
webpage = self._download_webpage(url, short_id)
real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
video_info = self.download_video_info(real_id)
chapters = video_info['chapters']
first_chapter = chapters[0]
if real_id_for_chapter(first_chapter) != real_id:
self.to_screen('Multipart video detected')
chapter_urls = []
for chapter in chapters:
chapter_id = real_id_for_chapter(chapter)
# Yes, when we this chapter is processed by WatIE,
# it will download the info again
chapter_info = self.download_video_info(chapter_id)
chapter_urls.append(chapter_info['url'])
entries = [self.url_result(chapter_url) for chapter_url in chapter_urls]
return self.playlist_result(entries, real_id, video_info['title'])
# Otherwise we can continue and extract just one part, we have to use
# the short id for getting the video url
player_data = compat_urllib_parse.urlencode({'shortVideoId': short_id,
'html5': '1'})
player_info = self._download_webpage('http://www.wat.tv/player?' + player_data,
real_id, u'Downloading player info')
player = json.loads(player_info)['player']
html5_player = self._html_search_regex(r'iframe src="(.*?)"', player,
'html5 player')
player_webpage = self._download_webpage(html5_player, real_id,
u'Downloading player webpage')
video_url = self._search_regex(r'urlhtml5 : "(.*?)"', player_webpage,
'video url')
info = {'id': real_id,
'url': video_url,
'ext': 'mp4',
'title': first_chapter['title'],
'thumbnail': first_chapter['preview'],
'description': first_chapter['description'],
'view_count': video_info['views'],
}
if 'date_diffusion' in first_chapter:
info['upload_date'] = unified_strdate(first_chapter['date_diffusion'])
return info

36
youtube_dl/extractor/wimp.py Normal file
View File

@ -0,0 +1,36 @@
import re
import base64
from .common import InfoExtractor
class WimpIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
_TEST = {
u'url': u'http://www.wimp.com/deerfence/',
u'file': u'deerfence.flv',
u'md5': u'8b215e2e0168c6081a1cf84b2846a2b5',
u'info_dict': {
u"title": u"Watch Till End: Herd of deer jump over a fence."
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
title = self._search_regex(r'<meta name="description" content="(.+?)" />',webpage, 'video title')
thumbnail_url = self._search_regex(r'<meta property="og\:image" content="(.+?)" />', webpage,'video thumbnail')
googleString = self._search_regex("googleCode = '(.*?)'", webpage, 'file url')
googleString = base64.b64decode(googleString).decode('ascii')
final_url = self._search_regex('","(.*?)"', googleString,'final video url')
ext = final_url.rpartition(u'.')[2]
return [{
'id': video_id,
'url': final_url,
'ext': ext,
'title': title,
'thumbnail': thumbnail_url,
}]

10
youtube_dl/extractor/worldstarhiphop.py
View File

@ -5,7 +5,15 @@ from .common import InfoExtractor
class WorldStarHipHopIE(InfoExtractor):
_VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
IE_NAME = u'WorldStarHipHop'
_TEST = {
"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!"
}
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)

10
youtube_dl/extractor/xhamster.py
View File

@ -11,6 +11,16 @@ from ..utils import (
class XHamsterIE(InfoExtractor):
"""Information Extractor for xHamster"""
_VALID_URL = r'(?:http://)?(?:www.)?xhamster\.com/movies/(?P<id>[0-9]+)/.*\.html'
_TEST = {
u'url': u'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
u'file': u'1509445.flv',
u'md5': u'9f48e0e8d58e3076bb236ff412ab62fa',
u'info_dict': {
u"upload_date": u"20121014",
u"uploader_id": u"Ruseful2011",
u"title": u"FemaleAgent Shy beauty takes the bait"
}
}
def _real_extract(self,url):
mobj = re.match(self._VALID_URL, url)

8
youtube_dl/extractor/xnxx.py
View File

@ -13,6 +13,14 @@ class XNXXIE(InfoExtractor):
VIDEO_URL_RE = r'flv_url=(.*?)&amp;'
VIDEO_TITLE_RE = r'<title>(.*?)\s+-\s+XNXX.COM'
VIDEO_THUMB_RE = r'url_bigthumb=(.*?)&amp;'
_TEST = {
u'url': u'http://video.xnxx.com/video1135332/lida_naked_funny_actress_5_',
u'file': u'1135332.flv',
u'md5': u'0831677e2b4761795f68d417e0b7b445',
u'info_dict': {
u"title": u"lida \u00bb Naked Funny Actress (5)"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

8
youtube_dl/extractor/xvideos.py
View File

@ -8,6 +8,14 @@ from ..utils import (
class XVideosIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?xvideos\.com/video([0-9]+)(?:.*)'
_TEST = {
u'url': u'http://www.xvideos.com/video939581/funny_porns_by_s_-1',
u'file': u'939581.flv',
u'md5': u'1d0c835822f0a71a7bf011855db929d0',
u'info_dict': {
u"title": u"Funny Porns By >>>>S<<<<<< -1"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

9
youtube_dl/extractor/yahoo.py
View File

@ -13,6 +13,15 @@ from ..utils import (
class YahooIE(InfoExtractor):
"""Information extractor for screen.yahoo.com."""
_VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
_TEST = {
u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
u'file': u'214727115.flv',
u'md5': u'2e717f169c1be93d84d3794a00d4a325',
u'info_dict': {
u"title": u"Julian Smith & Travis Legg Watch Julian Smith"
},
u'skip': u'Requires rtmpdump'
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

8
youtube_dl/extractor/youjizz.py
View File

@ -8,6 +8,14 @@ from ..utils import (
class YouJizzIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
_TEST = {
u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
u'file': u'2189178.flv',
u'md5': u'07e15fa469ba384c7693fd246905547c',
u'info_dict': {
u"title": u"Zeichentrick 1"
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)

12
youtube_dl/extractor/youku.py
View File

@ -1,3 +1,5 @@
# coding: utf-8
import json
import math
import random
@ -12,6 +14,16 @@ from ..utils import (
class YoukuIE(InfoExtractor):
_VALID_URL = r'(?:http://)?v\.youku\.com/v_show/id_(?P<ID>[A-Za-z0-9]+)\.html'
_TEST = {
u"url": u"http://v.youku.com/v_show/id_XNDgyMDQ2NTQw.html",
u"file": u"XNDgyMDQ2NTQw_part00.flv",
u"md5": u"ffe3f2e435663dc2d1eea34faeff5b5b",
u"params": { u"test": False },
u"info_dict": {
u"title": u"youtube-dl test video \"'/\\ä↭𝕐"
}
}
def _gen_sid(self):
nowTime = int(time.time() * 1000)

11
youtube_dl/extractor/youporn.py
View File

@ -16,6 +16,17 @@ from ..utils import (
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'info_dict': {
u"upload_date": u"20101221",
u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?",
u"uploader": u"Ask Dan And Jennifer",
u"title": u"Sex Ed: Is It Safe To Masturbate Daily?"
}
}
def _print_formats(self, formats):
"""Print all available formats"""

73
youtube_dl/extractor/youtube.py
View File

@ -81,6 +81,44 @@ class YoutubeIE(InfoExtractor):
'46': '1080x1920',
}
IE_NAME = u'youtube'
_TESTS = [
{
u"url": u"http://www.youtube.com/watch?v=BaW_jenozKc",
u"file": u"BaW_jenozKc.mp4",
u"info_dict": {
u"title": u"youtube-dl test video \"'/\\ä↭𝕐",
u"uploader": u"Philipp Hagemeister",
u"uploader_id": u"phihag",
u"upload_date": u"20121002",
u"description": u"test chars: \"'/\\ä↭𝕐\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de ."
}
},
{
u"url": u"http://www.youtube.com/watch?v=1ltcDfZMA3U",
u"file": u"1ltcDfZMA3U.flv",
u"note": u"Test VEVO video (#897)",
u"info_dict": {
u"upload_date": u"20070518",
u"title": u"Maps - It Will Find You",
u"description": u"Music video by Maps performing It Will Find You.",
u"uploader": u"MuteUSA",
u"uploader_id": u"MuteUSA"
}
},
{
u"url": u"http://www.youtube.com/watch?v=UxxajLWwzqY",
u"file": u"UxxajLWwzqY.mp4",
u"note": u"Test generic use_cipher_signature video (#897)",
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"uploader_id": u"IconaPop"
}
}
]
@classmethod
def suitable(cls, url):
@ -130,16 +168,25 @@ class YoutubeIE(InfoExtractor):
self.to_screen(u'RTMP download detected')
def _decrypt_signature(self, s):
"""Decrypt the key the two subkeys must have a length of 43"""
(a,b) = s.split('.')
if len(a) != 43 or len(b) != 43:
raise ExtractorError(u'Unable to decrypt signature, subkeys lengths %d.%d not supported; retrying might work' % (len(a), len(b)))
if self._downloader.params.get('verbose'):
self.to_screen('encrypted signature length %d.%d' % (len(a), len(b)))
b = ''.join([b[:8],a[0],b[9:18],b[-4],b[19:39], b[18]])[0:40]
a = a[-40:]
s_dec = '.'.join((a,b))[::-1]
return s_dec
"""Turn the encrypted s field into a working signature"""
if 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]
elif len(s) == 87:
return s[62] + s[82:62:-1] + s[83] + s[61:52:-1] + s[0] + s[51:2:-1]
elif len(s) == 86:
return s[2:63] + s[82] + s[64:82] + s[63]
elif len(s) == 85:
return s[76] + s[82:76:-1] + s[83] + s[75:60:-1] + s[0] + s[59:50:-1] + s[1] + s[49:2:-1]
elif len(s) == 84:
return s[83:36:-1] + s[2] + s[35:26:-1] + s[3] + s[25:3:-1] + s[26]
elif len(s) == 83:
return s[52] + s[81:55:-1] + s[2] + s[54:52:-1] + s[82] + s[51:36:-1] + s[55] + s[35:2:-1] + s[36]
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]
else:
raise ExtractorError(u'Unable to decrypt signature, key length %d not supported; retrying might work' % (len(s)))
def _get_available_subtitles(self, video_id):
self.report_video_subtitles_download(video_id)
@ -509,6 +556,12 @@ class YoutubeIE(InfoExtractor):
if 'sig' in url_data:
url += '&signature=' + url_data['sig'][0]
elif 's' in url_data:
if self._downloader.params.get('verbose'):
s = url_data['s'][0]
player = self._search_regex(r'html5player-(.+?)\.js', video_webpage,
'html5 player', fatal=False)
self.to_screen('encrypted signature length %d (%d.%d), itag %s, html5 player %s' %
(len(s), len(s.split('.')[0]), len(s.split('.')[1]), url_data['itag'][0], player))
signature = self._decrypt_signature(url_data['s'][0])
url += '&signature=' + signature
if 'ratebypass' not in url:

2
youtube_dl/utils.py
View File

@ -474,7 +474,7 @@ class ExtractorError(Exception):
""" tb, if given, is the original traceback (so that it can be printed out). """
if not sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
msg = msg + u'; please report this issue on http://yt-dl.org/bug'
msg = msg + u'; please report this issue on https://yt-dl.org/bug . Be sure to call youtube-dl with the --verbose flag and include its complete output.'
super(ExtractorError, self).__init__(msg)
self.traceback = tb

2
youtube_dl/version.py
View File

@ -1,2 +1,2 @@
__version__ = '2013.06.33'
__version__ = '2013.06.34.4'