mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2025-08-02 02:20:59 -05:00
Compare commits
57 Commits
2013.06.28
...
2013.06.34
Author | SHA1 | Date | |
---|---|---|---|
![]() |
e88f5e0b4e | ||
![]() |
769fda3c5a | ||
![]() |
23300d7149 | ||
![]() |
f5756f388a | ||
![]() |
ee313cdcbf | ||
![]() |
e38af9e00c | ||
![]() |
6b37f0be55 | ||
![]() |
6e5d5f2fc1 | ||
![]() |
75c9481224 | ||
![]() |
5746f9da99 | ||
![]() |
112da0a0ce | ||
![]() |
bcd606c0fe | ||
![]() |
ed92bc9f6e | ||
![]() |
9b0756f8f2 | ||
![]() |
aa0c87391c | ||
![]() |
b1dfdc51b1 | ||
![]() |
2e32528012 | ||
![]() |
f64e7695a1 | ||
![]() |
5abeaf0650 | ||
![]() |
8bcc355972 | ||
![]() |
6b4642fae3 | ||
![]() |
d1bd37deac | ||
![]() |
405ec05cb2 | ||
![]() |
52e8e1dc88 | ||
![]() |
b98a6b2f72 | ||
![]() |
0ca45b233f | ||
![]() |
65cceef8f4 | ||
![]() |
b004821fa9 | ||
![]() |
81b42336ad | ||
![]() |
c6c1974672 | ||
![]() |
a545d1d262 | ||
![]() |
037fcd0047 | ||
![]() |
318452bc0c | ||
![]() |
d746cd88c2 | ||
![]() |
9c42603b5a | ||
![]() |
ea93cce4f6 | ||
![]() |
f4daa18152 | ||
![]() |
9caa687d81 | ||
![]() |
3b58c6fb54 | ||
![]() |
5926c10690 | ||
![]() |
df725153d2 | ||
![]() |
d662896090 | ||
![]() |
db241e8645 | ||
![]() |
ead28ff30a | ||
![]() |
515d7a5e73 | ||
![]() |
14fbdc9cdd | ||
![]() |
98bcd2834a | ||
![]() |
f7ab6cbe16 | ||
![]() |
28ef06f7c2 | ||
![]() |
577d02370d | ||
![]() |
50be92c11c | ||
![]() |
d18596baf4 | ||
![]() |
7ce7e39476 | ||
![]() |
93eb15c573 | ||
![]() |
9f4d83e3b1 | ||
![]() |
1c251cd948 | ||
![]() |
70d1924f8b |
@@ -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'
|
||||
@@ -130,6 +132,7 @@ which means you can modify it, redistribute it or use it however you like.
|
||||
-u, --username USERNAME account username
|
||||
-p, --password PASSWORD account password
|
||||
-n, --netrc use .netrc authentication data
|
||||
--video-password PASSWORD video password (vimeo only)
|
||||
|
||||
## Post-processing Options:
|
||||
-x, --extract-audio convert video files to audio-only files (requires
|
||||
|
@@ -69,7 +69,9 @@ git checkout HEAD -- youtube-dl youtube-dl.exe
|
||||
|
||||
/bin/echo -e "\n### Signing and uploading the new binaries to youtube-dl.org..."
|
||||
for f in $RELEASE_FILES; do gpg --detach-sig "build/$version/$f"; done
|
||||
scp -r "build/$version" ytdl@youtube-dl.org:html/downloads/
|
||||
scp -r "build/$version" ytdl@yt-dl.org:html/tmp/
|
||||
ssh ytdl@yt-dl.org "mv html/tmp/$version html/downloads/"
|
||||
ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
|
||||
|
||||
/bin/echo -e "\n### Now switching to gh-pages..."
|
||||
git clone --branch gh-pages --single-branch . build/gh-pages
|
||||
|
76
devscripts/youtube_genalgo.py
Normal file
76
devscripts/youtube_genalgo.py
Normal file
@@ -0,0 +1,76 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
# Generate youtube signature algorithm from test cases
|
||||
|
||||
import sys
|
||||
|
||||
tests = [
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[]}|:;?/>.<",
|
||||
"J:|}][{=+-_)(*&;%$#@>MNBVCXZASDFGH^KLPOIUYTREWQ0987654321mnbvcxzasdfghrklpoiuytej"),
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$^&*()_-+={[]}|:;?/>.<",
|
||||
"!?;:|}][{=+-_)(*&^$#@/MNBVCXZASqFGHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"),
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[|};?/>.<",
|
||||
"ertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!/#$%^&*()_-+={[|};?@"),
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?/>.<",
|
||||
"{>/?;}[.=+-_)(*&^%$#@!MqBVCXZASDFwHJKLPOIUYTREWQ0987654321mnbvcxzasdfghjklpoiuytr"),
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!@#$%^&*()_-+={[};?>.<",
|
||||
"<.>?;}[{=+-_)(*&^%$#@!MNBVCXZASDFGHJKLPOIUYTREWe098765432rmnbvcxzasdfghjklpoiuyt1"),
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKJHGFDSAZXCVBNM!#$%^&*()_+={[};?/>.<",
|
||||
"D.>/?;}[{=+_)(*&^%$#!MNBVCXeAS<FGHJKLPOIUYTREWZ0987654321mnbvcxzasdfghjklpoiuytrQ"),
|
||||
("qwertyuioplkjhgfdsazxcvbnm1234567890QWERTYUIOPLKHGFDSAZXCVBNM!@#$%^&*(-+={[};?/>.<",
|
||||
"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()
|
33
test/helper.py
Normal file
33
test/helper.py
Normal file
@@ -0,0 +1,33 @@
|
||||
import io
|
||||
import json
|
||||
import os.path
|
||||
|
||||
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)
|
@@ -153,9 +153,11 @@ def generator(test_case):
|
||||
return test_template
|
||||
|
||||
### And add them to TestDownload
|
||||
for test_case in defs:
|
||||
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)
|
||||
setattr(TestDownload, test_method.__name__, test_method)
|
||||
del test_method
|
||||
|
||||
|
@@ -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
57
test/test_youtube_sig.py
Executable 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()
|
@@ -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
|
||||
@@ -100,7 +84,7 @@ class TestYoutubeSubtitles(unittest.TestCase):
|
||||
self.assertEqual(info_dict, None)
|
||||
def test_youtube_automatic_captions(self):
|
||||
DL = FakeYDL()
|
||||
DL.params['writesubtitles'] = True
|
||||
DL.params['writeautomaticsub'] = True
|
||||
DL.params['subtitleslang'] = 'it'
|
||||
IE = YoutubeIE(DL)
|
||||
info_dict = IE.extract('8YoUxe5ncPo')
|
||||
|
@@ -11,6 +11,32 @@
|
||||
"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",
|
||||
@@ -649,5 +675,44 @@
|
||||
"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"
|
||||
}
|
||||
},
|
||||
{
|
||||
"name": "CSpan",
|
||||
"url": "http://www.c-spanvideo.org/program/HolderonV",
|
||||
"file": "315139.flv",
|
||||
"md5": "74a623266956f69e4df0068ab6c80fe4",
|
||||
"info_dict": {
|
||||
"title": "Attorney General Eric Holder on Voting Rights Act Decision"
|
||||
},
|
||||
"skip": "Requires rtmpdump"
|
||||
},
|
||||
{
|
||||
"name": "Wimp",
|
||||
"url": "http://www.wimp.com/deerfence/",
|
||||
"file": "deerfence.flv",
|
||||
"md5": "8b215e2e0168c6081a1cf84b2846a2b5",
|
||||
"info_dict": {
|
||||
"title": "Watch Till End: Herd of deer jump over a fence."
|
||||
}
|
||||
}
|
||||
]
|
||||
|
@@ -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."""
|
||||
|
@@ -46,6 +46,7 @@ class YoutubeDL(object):
|
||||
|
||||
username: Username for authentication purposes.
|
||||
password: Password for authentication purposes.
|
||||
videopassword: Password for acces a video.
|
||||
usenetrc: Use netrc for authentication instead.
|
||||
verbose: Print additional info to stdout.
|
||||
quiet: Do not print messages to stdout.
|
||||
@@ -71,9 +72,10 @@ class YoutubeDL(object):
|
||||
writeinfojson: Write the video description to a .info.json file
|
||||
writethumbnail: Write the thumbnail image to a file
|
||||
writesubtitles: Write the video subtitles to a file
|
||||
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.
|
||||
@@ -473,7 +475,7 @@ class YoutubeDL(object):
|
||||
self.report_error(u'Cannot write description file ' + descfn)
|
||||
return
|
||||
|
||||
if self.params.get('writesubtitles', False) and 'subtitles' in info_dict and info_dict['subtitles']:
|
||||
if (self.params.get('writesubtitles', False) or self.params.get('writeautomaticsub')) and 'subtitles' in info_dict and info_dict['subtitles']:
|
||||
# subtitles download errors are already managed as troubles in relevant IE
|
||||
# that way it will silently go on when used with unsupporting IE
|
||||
subtitle = info_dict['subtitles'][0]
|
||||
|
@@ -25,6 +25,7 @@ __authors__ = (
|
||||
'M. Yasoob Ullah Khalid',
|
||||
'Julien Fraichard',
|
||||
'Johny Mo Swag',
|
||||
'Axel Noack',
|
||||
)
|
||||
|
||||
__license__ = 'Public Domain'
|
||||
@@ -172,6 +173,8 @@ def parseOpts(overrideArguments=None):
|
||||
dest='password', metavar='PASSWORD', help='account password')
|
||||
authentication.add_option('-n', '--netrc',
|
||||
action='store_true', dest='usenetrc', help='use .netrc authentication data', default=False)
|
||||
authentication.add_option('--video-password',
|
||||
dest='videopassword', metavar='PASSWORD', help='video password (vimeo only)')
|
||||
|
||||
|
||||
video_format.add_option('-f', '--format',
|
||||
@@ -188,6 +191,9 @@ def parseOpts(overrideArguments=None):
|
||||
video_format.add_option('--write-sub', '--write-srt',
|
||||
action='store_true', dest='writesubtitles',
|
||||
help='write subtitle file (currently youtube only)', default=False)
|
||||
video_format.add_option('--write-auto-sub', '--write-automatic-sub',
|
||||
action='store_true', dest='writeautomaticsub',
|
||||
help='write automatic subtitle file (currently youtube only)', default=False)
|
||||
video_format.add_option('--only-sub',
|
||||
action='store_true', dest='skip_download',
|
||||
help='[deprecated] alias of --skip-download', default=False)
|
||||
@@ -199,7 +205,7 @@ 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\'')
|
||||
@@ -319,7 +325,7 @@ def parseOpts(overrideArguments=None):
|
||||
if overrideArguments is not None:
|
||||
opts, args = parser.parse_args(overrideArguments)
|
||||
if opts.verbose:
|
||||
print(u'[debug] Override config: ' + repr(overrideArguments))
|
||||
sys.stderr.write(u'[debug] Override config: ' + repr(overrideArguments) + '\n')
|
||||
else:
|
||||
xdg_config_home = os.environ.get('XDG_CONFIG_HOME')
|
||||
if xdg_config_home:
|
||||
@@ -332,9 +338,9 @@ def parseOpts(overrideArguments=None):
|
||||
argv = systemConf + userConf + commandLineConf
|
||||
opts, args = parser.parse_args(argv)
|
||||
if opts.verbose:
|
||||
print(u'[debug] System config: ' + repr(systemConf))
|
||||
print(u'[debug] User config: ' + repr(userConf))
|
||||
print(u'[debug] Command-line args: ' + repr(commandLineConf))
|
||||
sys.stderr.write(u'[debug] System config: ' + repr(systemConf) + '\n')
|
||||
sys.stderr.write(u'[debug] User config: ' + repr(userConf) + '\n')
|
||||
sys.stderr.write(u'[debug] Command-line args: ' + repr(commandLineConf) + '\n')
|
||||
|
||||
return parser, opts, args
|
||||
|
||||
@@ -369,7 +375,7 @@ def _real_main(argv=None):
|
||||
|
||||
# Dump user agent
|
||||
if opts.dump_user_agent:
|
||||
print(std_headers['User-Agent'])
|
||||
compat_print(std_headers['User-Agent'])
|
||||
sys.exit(0)
|
||||
|
||||
# Batch file verification
|
||||
@@ -410,18 +416,18 @@ def _real_main(argv=None):
|
||||
|
||||
if opts.list_extractors:
|
||||
for ie in extractors:
|
||||
print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
|
||||
compat_print(ie.IE_NAME + (' (CURRENTLY BROKEN)' if not ie._WORKING else ''))
|
||||
matchedUrls = [url for url in all_urls if ie.suitable(url)]
|
||||
all_urls = [url for url in all_urls if url not in matchedUrls]
|
||||
for mu in matchedUrls:
|
||||
print(u' ' + mu)
|
||||
compat_print(u' ' + mu)
|
||||
sys.exit(0)
|
||||
|
||||
# Conflicting, missing and erroneous options
|
||||
if opts.usenetrc and (opts.username is not None or opts.password is not None):
|
||||
parser.error(u'using .netrc conflicts with giving username/password')
|
||||
if opts.password is not None and opts.username is None:
|
||||
print(u'WARNING: account username missing')
|
||||
parser.error(u' account username missing\n')
|
||||
if opts.outtmpl is not None and (opts.usetitle or opts.autonumber or opts.useid):
|
||||
parser.error(u'using output template conflicts with using title, video ID or auto number')
|
||||
if opts.usetitle and opts.useid:
|
||||
@@ -498,6 +504,7 @@ def _real_main(argv=None):
|
||||
'usenetrc': opts.usenetrc,
|
||||
'username': opts.username,
|
||||
'password': opts.password,
|
||||
'videopassword': opts.videopassword,
|
||||
'quiet': (opts.quiet or opts.geturl or opts.gettitle or opts.getid or opts.getthumbnail or opts.getdescription or opts.getfilename or opts.getformat),
|
||||
'forceurl': opts.geturl,
|
||||
'forcetitle': opts.gettitle,
|
||||
@@ -533,6 +540,7 @@ def _real_main(argv=None):
|
||||
'writeinfojson': opts.writeinfojson,
|
||||
'writethumbnail': opts.writethumbnail,
|
||||
'writesubtitles': opts.writesubtitles,
|
||||
'writeautomaticsub': opts.writeautomaticsub,
|
||||
'allsubtitles': opts.allsubtitles,
|
||||
'listsubtitles': opts.listsubtitles,
|
||||
'subtitlesformat': opts.subtitlesformat,
|
||||
|
@@ -4,8 +4,9 @@ from .arte import ArteTvIE
|
||||
from .bandcamp import BandcampIE
|
||||
from .bliptv import BlipTVIE, BlipTVUserIE
|
||||
from .breakcom import BreakIE
|
||||
from .comedycentral import ComedyCentralIE
|
||||
from .collegehumor import CollegeHumorIE
|
||||
from .comedycentral import ComedyCentralIE
|
||||
from .cspan import CSpanIE
|
||||
from .dailymotion import DailymotionIE
|
||||
from .depositfiles import DepositFilesIE
|
||||
from .eighttracks import EightTracksIE
|
||||
@@ -21,6 +22,7 @@ from .howcast import HowcastIE
|
||||
from .hypem import HypemIE
|
||||
from .ina import InaIE
|
||||
from .infoq import InfoQIE
|
||||
from .jukebox import JukeboxIE
|
||||
from .justintv import JustinTVIE
|
||||
from .keek import KeekIE
|
||||
from .liveleak import LiveLeakIE
|
||||
@@ -30,7 +32,6 @@ from .mtv import MTVIE
|
||||
from .myspass import MySpassIE
|
||||
from .myvideo import MyVideoIE
|
||||
from .nba import NBAIE
|
||||
from .statigram import StatigramIE
|
||||
from .photobucket import PhotobucketIE
|
||||
from .pornotube import PornotubeIE
|
||||
from .rbmaradio import RBMARadioIE
|
||||
@@ -38,17 +39,21 @@ from .redtube import RedTubeIE
|
||||
from .soundcloud import SoundcloudIE, SoundcloudSetIE
|
||||
from .spiegel import SpiegelIE
|
||||
from .stanfordoc import StanfordOpenClassroomIE
|
||||
from .statigram import StatigramIE
|
||||
from .steam import SteamIE
|
||||
from .teamcoco import TeamcocoIE
|
||||
from .ted import TEDIE
|
||||
from .tudou import TudouIE
|
||||
from .tumblr import TumblrIE
|
||||
from .ustream import UstreamIE
|
||||
from .vbox7 import Vbox7IE
|
||||
from .vevo import VevoIE
|
||||
from .vimeo import VimeoIE
|
||||
from .vine import VineIE
|
||||
from .wimp import WimpIE
|
||||
from .worldstarhiphop import WorldStarHipHopIE
|
||||
from .xnxx import XNXXIE
|
||||
from .xhamster import XHamsterIE
|
||||
from .xnxx import XNXXIE
|
||||
from .xvideos import XVideosIE
|
||||
from .yahoo import YahooIE, YahooSearchIE
|
||||
from .youjizz import YouJizzIE
|
||||
@@ -57,6 +62,7 @@ from .youporn import YouPornIE
|
||||
from .youtube import YoutubeIE, YoutubePlaylistIE, YoutubeSearchIE, YoutubeUserIE, YoutubeChannelIE
|
||||
from .zdf import ZDFIE
|
||||
|
||||
|
||||
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.
|
||||
@@ -125,6 +131,11 @@ def gen_extractors():
|
||||
GametrailersIE(),
|
||||
StatigramIE(),
|
||||
BreakIE(),
|
||||
VevoIE(),
|
||||
JukeboxIE(),
|
||||
TudouIE(),
|
||||
CSpanIE(),
|
||||
WimpIE(),
|
||||
GenericIE()
|
||||
]
|
||||
|
||||
|
@@ -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
|
||||
|
@@ -172,7 +172,7 @@ class ComedyCentralIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'format': format,
|
||||
'thumbnail': None,
|
||||
'description': officialTitle,
|
||||
'description': compat_str(officialTitle),
|
||||
}
|
||||
results.append(info)
|
||||
|
||||
|
@@ -211,7 +211,7 @@ class InfoExtractor(object):
|
||||
raise ExtractorError(u'Unable to extract %s' % _name)
|
||||
else:
|
||||
self._downloader.report_warning(u'unable to extract %s; '
|
||||
u'please report this issue on GitHub.' % _name)
|
||||
u'please report this issue on http://yt-dl.org/bug' % _name)
|
||||
return None
|
||||
|
||||
def _html_search_regex(self, pattern, string, name, default=None, fatal=True, flags=0):
|
||||
|
44
youtube_dl/extractor/cspan.py
Normal file
44
youtube_dl/extractor/cspan.py
Normal file
@@ -0,0 +1,44 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
compat_urllib_parse,
|
||||
)
|
||||
|
||||
class CSpanIE(InfoExtractor):
|
||||
_VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
|
||||
|
||||
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,
|
||||
}
|
@@ -46,14 +46,18 @@ class GooglePlusIE(InfoExtractor):
|
||||
video_title = self._html_search_regex(r'<meta name\=\"Description\" content\=\"(.*?)[\n<"]',
|
||||
webpage, 'title', default=u'NA')
|
||||
|
||||
# Step 2, Stimulate clicking the image box to launch video
|
||||
video_page = self._search_regex('"(https\://plus\.google\.com/photos/.*?)",,"image/jpeg","video"\]',
|
||||
# Step 2, Simulate clicking the image box to launch video
|
||||
DOMAIN = 'https://plus.google.com'
|
||||
video_page = self._search_regex(r'<a href="((?:%s)?/photos/.*?)"' % re.escape(DOMAIN),
|
||||
webpage, u'video page URL')
|
||||
if not video_page.startswith(DOMAIN):
|
||||
video_page = DOMAIN + video_page
|
||||
|
||||
webpage = self._download_webpage(video_page, video_id, u'Downloading video page')
|
||||
|
||||
# Extract video links on video page
|
||||
"""Extract video links of all sizes"""
|
||||
pattern = '\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
|
||||
pattern = r'\d+,\d+,(\d+),"(http\://redirector\.googlevideo\.com.*?)"'
|
||||
mobj = re.findall(pattern, webpage)
|
||||
if len(mobj) == 0:
|
||||
raise ExtractorError(u'Unable to extract video links')
|
||||
|
56
youtube_dl/extractor/jukebox.py
Normal file
56
youtube_dl/extractor/jukebox.py
Normal file
@@ -0,0 +1,56 @@
|
||||
# coding: utf-8
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
unescapeHTML,
|
||||
)
|
||||
|
||||
class JukeboxIE(InfoExtractor):
|
||||
_VALID_URL = r'^http://www\.jukebox?\..+?\/.+[,](?P<video_id>[a-z0-9\-]+).html'
|
||||
_IFRAME = r'<iframe .*src="(?P<iframe>[^"]*)".*>'
|
||||
_VIDEO_URL = r'"config":{"file":"(?P<video_url>http:[^"]+[.](?P<video_ext>[^.?]+)[?]mdtk=[0-9]+)"'
|
||||
_TITLE = r'<h1 class="inline">(?P<title>[^<]+)</h1>.*<span id="infos_article_artist">(?P<artist>[^<]+)</span>'
|
||||
_IS_YOUTUBE = r'config":{"file":"(?P<youtube_url>http:[\\][/][\\][/]www[.]youtube[.]com[\\][/]watch[?]v=[^"]+)"'
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('video_id')
|
||||
|
||||
html = self._download_webpage(url, video_id)
|
||||
|
||||
mobj = re.search(self._IFRAME, html)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Cannot extract iframe url')
|
||||
iframe_url = unescapeHTML(mobj.group('iframe'))
|
||||
|
||||
iframe_html = self._download_webpage(iframe_url, video_id, 'Downloading iframe')
|
||||
mobj = re.search(r'class="jkb_waiting"', iframe_html)
|
||||
if mobj is not None:
|
||||
raise ExtractorError(u'Video is not available(in your country?)!')
|
||||
|
||||
self.report_extraction(video_id)
|
||||
|
||||
mobj = re.search(self._VIDEO_URL, iframe_html)
|
||||
if mobj is None:
|
||||
mobj = re.search(self._IS_YOUTUBE, iframe_html)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Cannot extract video url')
|
||||
youtube_url = unescapeHTML(mobj.group('youtube_url')).replace('\/','/')
|
||||
self.to_screen(u'Youtube video detected')
|
||||
return self.url_result(youtube_url,ie='Youtube')
|
||||
video_url = unescapeHTML(mobj.group('video_url')).replace('\/','/')
|
||||
video_ext = unescapeHTML(mobj.group('video_ext'))
|
||||
|
||||
mobj = re.search(self._TITLE, html)
|
||||
if mobj is None:
|
||||
raise ExtractorError(u'Cannot extract title')
|
||||
title = unescapeHTML(mobj.group('title'))
|
||||
artist = unescapeHTML(mobj.group('artist'))
|
||||
|
||||
return [{'id': video_id,
|
||||
'url': video_url,
|
||||
'title': artist + '-' + title,
|
||||
'ext': video_ext
|
||||
}]
|
@@ -27,6 +27,14 @@ class MTVIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
# Some videos come from Vevo.com
|
||||
m_vevo = re.search(r'isVevoVideo = true;.*?vevoVideoId = "(.*?)";',
|
||||
webpage, re.DOTALL)
|
||||
if m_vevo:
|
||||
vevo_id = m_vevo.group(1);
|
||||
self.to_screen(u'Vevo video detected: %s' % vevo_id)
|
||||
return self.url_result('vevo:%s' % vevo_id, ie='Vevo')
|
||||
|
||||
#song_name = self._html_search_regex(r'<meta name="mtv_vt" content="([^"]+)"/>',
|
||||
# webpage, u'song name', fatal=False)
|
||||
|
||||
|
32
youtube_dl/extractor/tudou.py
Normal file
32
youtube_dl/extractor/tudou.py
Normal file
@@ -0,0 +1,32 @@
|
||||
import re
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class TudouIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:http://)?(?:www\.)?tudou\.com/(?:listplay|programs)/(?:view|(.+?))/(?:([^/]+)|([^/]+)\.html)'
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group(2).replace('.html','')
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
video_id = re.search('"k":(.+?),',webpage).group(1)
|
||||
title = re.search(",kw:\"(.+)\"",webpage)
|
||||
if title is None:
|
||||
title = re.search(",kw: \'(.+)\'",webpage)
|
||||
title = title.group(1)
|
||||
thumbnail_url = re.search(",pic: \'(.+?)\'",webpage)
|
||||
if thumbnail_url is None:
|
||||
thumbnail_url = re.search(",pic:\"(.+?)\"",webpage)
|
||||
thumbnail_url = thumbnail_url.group(1)
|
||||
info_url = "http://v2.tudou.com/f?id="+str(video_id)
|
||||
webpage = self._download_webpage(info_url, video_id, "Opening the info webpage")
|
||||
final_url = re.search('\>(.+?)\<\/f\>',webpage).group(1)
|
||||
ext = (final_url.split('?')[0]).split('.')[-1]
|
||||
return [{
|
||||
'id': video_id,
|
||||
'url': final_url,
|
||||
'ext': ext,
|
||||
'title': title,
|
||||
'thumbnail': thumbnail_url,
|
||||
}]
|
43
youtube_dl/extractor/vevo.py
Normal file
43
youtube_dl/extractor/vevo.py
Normal file
@@ -0,0 +1,43 @@
|
||||
import re
|
||||
import json
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
)
|
||||
|
||||
class VevoIE(InfoExtractor):
|
||||
"""
|
||||
Accecps urls from vevo.com or in the format 'vevo:{id}'
|
||||
(currently used by MTVIE)
|
||||
"""
|
||||
_VALID_URL = r'((http://www.vevo.com/watch/.*?/.*?/)|(vevo:))(?P<id>.*)$'
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
video_id = mobj.group('id')
|
||||
|
||||
json_url = 'http://www.vevo.com/data/video/%s' % video_id
|
||||
base_url = 'http://smil.lvl3.vevo.com'
|
||||
videos_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (base_url, video_id, video_id.lower())
|
||||
info_json = self._download_webpage(json_url, video_id, u'Downloading json info')
|
||||
links_webpage = self._download_webpage(videos_url, video_id, u'Downloading videos urls')
|
||||
|
||||
self.report_extraction(video_id)
|
||||
video_info = json.loads(info_json)
|
||||
m_urls = list(re.finditer(r'<video src="(?P<ext>.*?):(?P<url>.*?)"', links_webpage))
|
||||
if m_urls is None or len(m_urls) == 0:
|
||||
raise ExtractorError(u'Unable to extract video url')
|
||||
# They are sorted from worst to best quality
|
||||
m_url = m_urls[-1]
|
||||
video_url = base_url + m_url.group('url')
|
||||
ext = m_url.group('ext')
|
||||
|
||||
return {'url': video_url,
|
||||
'ext': ext,
|
||||
'id': video_id,
|
||||
'title': video_info['title'],
|
||||
'thumbnail': video_info['img'],
|
||||
'upload_date': video_info['launchDate'].replace('/',''),
|
||||
'uploader': video_info['Artists'][0]['title'],
|
||||
}
|
@@ -20,9 +20,9 @@ class VimeoIE(InfoExtractor):
|
||||
IE_NAME = u'vimeo'
|
||||
|
||||
def _verify_video_password(self, url, video_id, webpage):
|
||||
password = self._downloader.params.get('password', None)
|
||||
password = self._downloader.params.get('videopassword', None)
|
||||
if password is None:
|
||||
raise ExtractorError(u'This video is protected by a password, use the --password option')
|
||||
raise ExtractorError(u'This video is protected by a password, use the --video-password option')
|
||||
token = re.search(r'xsrft: \'(.*?)\'', webpage).group(1)
|
||||
data = compat_urllib_parse.urlencode({'password': password,
|
||||
'token': token})
|
||||
|
28
youtube_dl/extractor/wimp.py
Normal file
28
youtube_dl/extractor/wimp.py
Normal file
@@ -0,0 +1,28 @@
|
||||
import re
|
||||
import base64
|
||||
|
||||
from .common import InfoExtractor
|
||||
|
||||
|
||||
class WimpIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:http://)?(?:www\.)?wimp\.com/([^/]+)/'
|
||||
|
||||
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,
|
||||
}]
|
||||
|
@@ -16,6 +16,10 @@ class WorldStarHipHopIE(InfoExtractor):
|
||||
video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
|
||||
webpage_src, u'video URL')
|
||||
|
||||
if 'youtube' in video_url:
|
||||
self.to_screen(u'Youtube video detected:')
|
||||
return self.url_result(video_url, ie='Youtube')
|
||||
|
||||
if 'mp4' in video_url:
|
||||
ext = 'mp4'
|
||||
else:
|
||||
|
@@ -129,16 +129,26 @@ class YoutubeIE(InfoExtractor):
|
||||
"""Indicate the download will use the RTMP protocol."""
|
||||
self.to_screen(u'RTMP download detected')
|
||||
|
||||
@staticmethod
|
||||
def _decrypt_signature(s):
|
||||
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 not valid')
|
||||
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
|
||||
|
||||
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, subkeys length %d not supported; retrying might work' % (len(s)))
|
||||
|
||||
def _get_available_subtitles(self, video_id):
|
||||
self.report_video_subtitles_download(video_id)
|
||||
@@ -453,14 +463,13 @@ class YoutubeIE(InfoExtractor):
|
||||
if video_subtitles:
|
||||
(sub_error, sub_lang, sub) = video_subtitles[0]
|
||||
if sub_error:
|
||||
# We try with the automatic captions
|
||||
video_subtitles = self._request_automatic_caption(video_id, video_webpage)
|
||||
(sub_error_auto, sub_lang, sub) = video_subtitles[0]
|
||||
if sub is not None:
|
||||
pass
|
||||
else:
|
||||
# We report the original error
|
||||
self._downloader.report_warning(sub_error)
|
||||
self._downloader.report_warning(sub_error)
|
||||
|
||||
if self._downloader.params.get('writeautomaticsub', False):
|
||||
video_subtitles = self._request_automatic_caption(video_id, video_webpage)
|
||||
(sub_error, sub_lang, sub) = video_subtitles[0]
|
||||
if sub_error:
|
||||
self._downloader.report_warning(sub_error)
|
||||
|
||||
if self._downloader.params.get('allsubtitles', False):
|
||||
video_subtitles = self._extract_all_subtitles(video_id)
|
||||
@@ -484,11 +493,15 @@ class YoutubeIE(InfoExtractor):
|
||||
|
||||
try:
|
||||
mobj = re.search(r';ytplayer.config = ({.*?});', video_webpage)
|
||||
if not mobj:
|
||||
raise ValueError('Could not find vevo ID')
|
||||
info = json.loads(mobj.group(1))
|
||||
args = info['args']
|
||||
if args.get('ptk','') == 'vevo' or 'dashmpd' in args:
|
||||
# Vevo videos with encrypted signatures
|
||||
self.to_screen(u'%s: Vevo video detected.' % video_id)
|
||||
# Easy way to know if the 's' value is in url_encoded_fmt_stream_map
|
||||
# this signatures are encrypted
|
||||
m_s = re.search(r'[&,]s=', args['url_encoded_fmt_stream_map'])
|
||||
if m_s is not None:
|
||||
self.to_screen(u'%s: Encrypted signatures detected.' % video_id)
|
||||
video_info['url_encoded_fmt_stream_map'] = [args['url_encoded_fmt_stream_map']]
|
||||
except ValueError:
|
||||
pass
|
||||
@@ -505,6 +518,12 @@ 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:
|
||||
|
@@ -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 GitHub.'
|
||||
msg = msg + u'; please report this issue on http://yt-dl.org/bug'
|
||||
super(ExtractorError, self).__init__(msg)
|
||||
|
||||
self.traceback = tb
|
||||
|
@@ -1,2 +1,2 @@
|
||||
|
||||
__version__ = '2013.06.28'
|
||||
__version__ = '2013.06.34'
|
||||
|
Reference in New Issue
Block a user