1
0
mirror of https://gitlab.com/ytdl-org/youtube-dl.git synced 2026-04-29 00:00:03 -04:00

Compare commits

...

26 Commits

Author SHA1 Message Date
Philipp Hagemeister fdb7ca3b8d release 2014.02.26 2014-02-26 00:32:22 +01:00
Philipp Hagemeister 0d7caf5cdf Merge remote-tracking branch 'ruuk/master' 2014-02-26 00:31:08 +01:00
Philipp Hagemeister a339d7ba91 Credit @amlweems for ocw.mit (#2460) 2014-02-26 00:30:47 +01:00
Philipp Hagemeister 7216de55d6 [mit] Fix ocw tests 2014-02-26 00:29:45 +01:00
Philipp Hagemeister 2437fbca64 [tests] Raise an exception if test definition is invalid (Found in #2460) 2014-02-26 00:12:02 +01:00
Philipp Hagemeister 7d75d06b78 Merge branch 'ocw-mit-edu' of https://github.com/amlweems/youtube-dl 2014-02-26 00:09:42 +01:00
Philipp Hagemeister 13ef5648c4 Merge branch 'master' of github.com:rg3/youtube-dl 2014-02-26 00:07:45 +01:00
Philipp Hagemeister 5b2478e2ba [mit] Modernize 2014-02-26 00:06:31 +01:00
Jaime Marquínez Ferrándiz 8b286571c3 [mixcloud] Fix _VALID_RE (fixes #2462)
Accept any character except `/` for uploader and the name, caused problems with non ASCII characters
2014-02-26 00:04:03 +01:00
Jaime Marquínez Ferrándiz f3ac523794 Merge pull request #2461 from niebles/master
Update __init__.py

`io` wasn't imported.
2014-02-26 00:00:57 +01:00
Jaime Marquínez Ferrándiz 020cf5ebfd [nbc] Add an extractor for the main nbc.com site
Some of the videos are encrypted, the f4m downloader doesn’t support them.
2014-02-25 23:57:54 +01:00
ruuk 54ab193970 Extract thumbnail with _og_search_thumbnail 2014-02-25 14:41:36 -08:00
niebles 8f563f32ab Update __init__.py 2014-02-25 17:31:16 -05:00
Anthony Weems 151bae3566 Add support for ocw.mit.edu video lectures 2014-02-25 14:44:34 -06:00
ruuk 76df418cba Add thumbnail for metacafe 2014-02-25 12:04:44 -08:00
Jaime Marquínez Ferrándiz d0a72674c6 [crunchyroll] Use enumerate 2014-02-25 20:51:51 +01:00
Sergey M. 1d430674c7 [crunchyroll] Handle error message 2014-02-25 20:30:17 +07:00
Sergey M 70cb73922b [crunchyroll] Fix subtitle lang code extraction 2014-02-25 20:29:53 +07:00
Sergey M 344400951c [crunchyroll] Tidy and modernize 2014-02-25 20:29:53 +07:00
Jaime Marquínez Ferrándiz ea5a0be811 Skip youtube toptracks test
All the playlists return 500 errors.
2014-02-25 14:11:01 +01:00
Philipp Hagemeister 3c7fd0bdb2 release 2014.02.25.1 2014-02-25 11:15:55 +01:00
Philipp Hagemeister 6cadf8c858 [vevo] Add age_limit support 2014-02-25 11:15:34 +01:00
Philipp Hagemeister 27579b9e4c [vevo] Add suppot for v3 SMIL URLs (Fixes #2409) 2014-02-25 11:06:47 +01:00
Philipp Hagemeister 4d756a9cc0 [testurl] Fix case when only one IE matches 2014-02-25 10:43:34 +01:00
Philipp Hagemeister 3e668e05be Merge pull request #2456 from AGSPhoenix/master
[YT] Fix incorrect format code descriptions
2014-02-25 10:24:02 +01:00
AGSPhoenix 60d3a2e0f8 Fix incorrect format codes
Corrects the descriptions for the DASH video format codes 264 and 138
(1440p and 2160p, respectively).
2014-02-24 21:29:37 -05:00
14 changed files with 232 additions and 57 deletions
+1 -3
View File
@@ -73,9 +73,7 @@ def generator(test_case):
if 'playlist' not in test_case:
info_dict = test_case.get('info_dict', {})
if not test_case.get('file') and not (info_dict.get('id') and info_dict.get('ext')):
print_skipping('The output file cannot be know, the "file" '
'key is missing or the info_dict is incomplete')
return
raise Exception('Test definition incorrect. The output file cannot be known. Are both \'id\' and \'ext\' keys present?')
if 'skip' in test_case:
print_skipping(test_case['skip'])
return
+2
View File
@@ -118,6 +118,8 @@ class TestYoutubeLists(unittest.TestCase):
self.assertEqual(original_video['id'], 'rjFaenf1T-Y')
def test_youtube_toptracks(self):
print('Skipping: The playlist page gives error 500')
return
dl = FakeYDL()
ie = YoutubePlaylistIE(dl)
result = ie.extract('https://www.youtube.com/playlist?list=MCUS')
+2
View File
@@ -47,12 +47,14 @@ __authors__ = (
'Michael Kaiser',
'Niklas Laxström',
'David Triendl',
'Anthony Weems',
)
__license__ = 'Public Domain'
import codecs
import getpass
import io
import locale
import optparse
import os
+5 -2
View File
@@ -137,7 +137,7 @@ from .malemotion import MalemotionIE
from .mdr import MDRIE
from .metacafe import MetacafeIE
from .metacritic import MetacriticIE
from .mit import TechTVMITIE, MITIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mixcloud import MixcloudIE
from .mpora import MporaIE
from .mofosex import MofosexIE
@@ -152,7 +152,10 @@ from .myspass import MySpassIE
from .myvideo import MyVideoIE
from .naver import NaverIE
from .nba import NBAIE
from .nbc import NBCNewsIE
from .nbc import (
NBCIE,
NBCNewsIE,
)
from .ndr import NDRIE
from .ndtv import NDTVIE
from .newgrounds import NewgroundsIE
+21 -11
View File
@@ -1,7 +1,11 @@
# encoding: utf-8
from __future__ import unicode_literals
import re, base64, zlib
import re
import json
import base64
import zlib
from hashlib import sha1
from math import pow, sqrt, floor
from .common import InfoExtractor
@@ -19,13 +23,15 @@ from ..aes import (
inc,
)
class CrunchyrollIE(InfoExtractor):
_VALID_URL = r'(?:https?://)?(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_TESTS = [{
_VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:[^/]*/[^/?&]*?|media/\?id=)(?P<video_id>[0-9]+))(?:[/?&]|$)'
_TEST = {
'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513',
'file': '645513.flv',
#'md5': 'b1639fd6ddfaa43788c85f6d1dddd412',
'info_dict': {
'id': '645513',
'ext': 'flv',
'title': 'Wanna be the Strongest in the World Episode 1 An Idol-Wrestler is Born!',
'description': 'md5:2d17137920c64f2f49981a7797d275ef',
'thumbnail': 'http://img1.ak.crunchyroll.com/i/spire1-tmb/20c6b5e10f1a47b10516877d3c039cae1380951166_full.jpg',
@@ -36,7 +42,7 @@ class CrunchyrollIE(InfoExtractor):
# rtmp
'skip_download': True,
},
}]
}
_FORMAT_IDS = {
'360': ('60', '106'),
@@ -68,7 +74,7 @@ class CrunchyrollIE(InfoExtractor):
shaHash = bytes_to_intlist(sha1(prefix + str(num4).encode('ascii')).digest())
# Extend 160 Bit hash to 256 Bit
return shaHash + [0] * 12
key = obfuscate_key(id)
class Counter:
__value = iv
@@ -80,9 +86,8 @@ class CrunchyrollIE(InfoExtractor):
return zlib.decompress(decrypted_data)
def _convert_subtitles_to_srt(self, subtitles):
i=1
output = ''
for start, end, text in re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles):
for i, (start, end, text) in enumerate(re.findall(r'<event [^>]*?start="([^"]+)" [^>]*?end="([^"]+)" [^>]*?text="([^"]+)"[^>]*?>', subtitles), 1):
start = start.replace('.', ',')
end = end.replace('.', ',')
text = clean_html(text)
@@ -90,7 +95,6 @@ class CrunchyrollIE(InfoExtractor):
if not text:
continue
output += '%d\n%s --> %s\n%s\n\n' % (i, start, end, text)
i+=1
return output
def _real_extract(self,url):
@@ -108,6 +112,12 @@ class CrunchyrollIE(InfoExtractor):
if note_m:
raise ExtractorError(note_m)
mobj = re.search(r'Page\.messaging_box_controller\.addItems\(\[(?P<msg>{.+?})\]\)', webpage)
if mobj:
msg = json.loads(mobj.group('msg'))
if msg.get('type') == 'error':
raise ExtractorError('crunchyroll returned error: %s' % msg['message_body'], expected=True)
video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL)
video_title = re.sub(r' {2,}', ' ', video_title)
video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='')
@@ -123,7 +133,7 @@ class CrunchyrollIE(InfoExtractor):
playerdata_req.data = compat_urllib_parse.urlencode({'current_page': webpage_url})
playerdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
playerdata = self._download_webpage(playerdata_req, video_id, note='Downloading media info')
stream_id = self._search_regex(r'<media_id>([^<]+)', playerdata, 'stream_id')
video_thumbnail = self._search_regex(r'<episode_image_url>([^<]+)', playerdata, 'thumbnail', fatal=False)
@@ -161,7 +171,7 @@ class CrunchyrollIE(InfoExtractor):
data = base64.b64decode(data)
subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8')
lang_code = self._search_regex(r'lang_code=\'([^\']+)', subtitle, 'subtitle_lang_code', fatal=False)
lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False)
if not lang_code:
continue
subtitles[lang_code] = self._convert_subtitles_to_srt(subtitle)
+2
View File
@@ -166,6 +166,7 @@ class MetacafeIE(InfoExtractor):
video_title = self._html_search_regex(r'(?im)<title>(.*) - Video</title>', webpage, u'title')
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
video_uploader = self._html_search_regex(
r'submitter=(.*?);|googletag\.pubads\(\)\.setTargeting\("(?:channel|submiter)","([^"]+)"\);',
webpage, u'uploader nickname', fatal=False)
@@ -183,6 +184,7 @@ class MetacafeIE(InfoExtractor):
'uploader': video_uploader,
'upload_date': None,
'title': video_title,
'thumbnail':thumbnail,
'ext': video_ext,
'age_limit': age_limit,
}
+105 -30
View File
@@ -1,24 +1,29 @@
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from .youtube import YoutubeIE
from ..utils import (
compat_urlparse,
clean_html,
get_element_by_id,
)
class TechTVMITIE(InfoExtractor):
IE_NAME = u'techtv.mit.edu'
IE_NAME = 'techtv.mit.edu'
_VALID_URL = r'https?://techtv\.mit\.edu/(videos|embeds)/(?P<id>\d+)'
_TEST = {
u'url': u'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
u'file': u'25418.mp4',
u'md5': u'1f8cb3e170d41fd74add04d3c9330e5f',
u'info_dict': {
u'title': u'MIT DNA Learning Center Set',
u'description': u'md5:82313335e8a8a3f243351ba55bc1b474',
'url': 'http://techtv.mit.edu/videos/25418-mit-dna-learning-center-set',
'md5': '1f8cb3e170d41fd74add04d3c9330e5f',
'info_dict': {
'id': '25418',
'ext': 'mp4',
'title': 'MIT DNA Learning Center Set',
'description': 'md5:82313335e8a8a3f243351ba55bc1b474',
},
}
@@ -27,12 +32,12 @@ class TechTVMITIE(InfoExtractor):
video_id = mobj.group('id')
raw_page = self._download_webpage(
'http://techtv.mit.edu/videos/%s' % video_id, video_id)
clean_page = re.compile(u'<!--.*?-->', re.S).sub(u'', raw_page)
clean_page = re.compile(r'<!--.*?-->', re.S).sub('', raw_page)
base_url = self._search_regex(r'ipadUrl: \'(.+?cloudfront.net/)',
raw_page, u'base url')
formats_json = self._search_regex(r'bitrates: (\[.+?\])', raw_page,
u'video formats')
base_url = self._search_regex(
r'ipadUrl: \'(.+?cloudfront.net/)', raw_page, 'base url')
formats_json = self._search_regex(
r'bitrates: (\[.+?\])', raw_page, 'video formats')
formats_mit = json.loads(formats_json)
formats = [
{
@@ -48,28 +53,32 @@ class TechTVMITIE(InfoExtractor):
title = get_element_by_id('edit-title', clean_page)
description = clean_html(get_element_by_id('edit-description', clean_page))
thumbnail = self._search_regex(r'playlist:.*?url: \'(.+?)\'',
raw_page, u'thumbnail', flags=re.DOTALL)
thumbnail = self._search_regex(
r'playlist:.*?url: \'(.+?)\'',
raw_page, 'thumbnail', flags=re.DOTALL)
return {'id': video_id,
'title': title,
'formats': formats,
'description': description,
'thumbnail': thumbnail,
}
return {
'id': video_id,
'title': title,
'formats': formats,
'description': description,
'thumbnail': thumbnail,
}
class MITIE(TechTVMITIE):
IE_NAME = u'video.mit.edu'
IE_NAME = 'video.mit.edu'
_VALID_URL = r'https?://video\.mit\.edu/watch/(?P<title>[^/]+)'
_TEST = {
u'url': u'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
u'file': u'21783.mp4',
u'md5': u'7db01d5ccc1895fc5010e9c9e13648da',
u'info_dict': {
u'title': u'The Government is Profiling You',
u'description': u'md5:ad5795fe1e1623b73620dbfd47df9afd',
'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
'file': '.mp4',
'md5': '7db01d5ccc1895fc5010e9c9e13648da',
'info_dict': {
'id': '21783',
'ext': 'mp4',
'title': 'The Government is Profiling You',
'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
},
}
@@ -77,7 +86,73 @@ class MITIE(TechTVMITIE):
mobj = re.match(self._VALID_URL, url)
page_title = mobj.group('title')
webpage = self._download_webpage(url, page_title)
self.to_screen('%s: Extracting %s url' % (page_title, TechTVMITIE.IE_NAME))
embed_url = self._search_regex(r'<iframe .*?src="(.+?)"', webpage,
u'embed url')
embed_url = self._search_regex(
r'<iframe .*?src="(.+?)"', webpage, 'embed url')
return self.url_result(embed_url, ie='TechTVMIT')
class OCWMITIE(InfoExtractor):
IE_NAME = 'ocw.mit.edu'
_VALID_URL = r'^http://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
_BASE_URL = 'http://ocw.mit.edu/'
_TESTS = [
{
'url': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/',
'info_dict': {
'id': 'EObHWIEKGjA',
'ext': 'mp4',
'title': 'Lecture 7: Multiple Discrete Random Variables: Expectations, Conditioning, Independence',
'description': 'In this lecture, the professor discussed multiple random variables, expectations, and binomial distribution.',
#'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt'
}
},
{
'url': 'http://ocw.mit.edu/courses/mathematics/18-01sc-single-variable-calculus-fall-2010/1.-differentiation/part-a-definition-and-basic-rules/session-1-introduction-to-derivatives/',
'info_dict': {
'id': '7K1sB05pE0A',
'ext': 'mp4',
'title': 'Session 1: Introduction to Derivatives',
'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.',
#'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT'
}
}
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
topic = mobj.group('topic')
webpage = self._download_webpage(url, topic)
title = self._html_search_meta('WT.cg_s', webpage)
description = self._html_search_meta('Description', webpage)
# search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, start, stop, captions_file)
embed_chapter_media = re.search(r'ocw_embed_chapter_media\((.+?)\)', webpage)
if embed_chapter_media:
metadata = re.sub(r'[\'"]', '', embed_chapter_media.group(1))
metadata = re.split(r', ?', metadata)
yt = metadata[1]
subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7])
else:
# search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file)
embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage)
if embed_media:
metadata = re.sub(r'[\'"]', '', embed_media.group(1))
metadata = re.split(r', ?', metadata)
yt = metadata[1]
subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5])
else:
raise ExtractorError('Unable to find embedded YouTube video.')
video_id = YoutubeIE.extract_id(yt)
return {
'_type': 'url_transparent',
'id': video_id,
'title': title,
'description': description,
'url': yt,
'url_transparent'
'subtitles': subs,
'ie_key': 'Youtube',
}
+1 -1
View File
@@ -10,7 +10,7 @@ from ..utils import (
class MixcloudIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
IE_NAME = 'mixcloud'
_TEST = {
+24
View File
@@ -6,6 +6,30 @@ from .common import InfoExtractor
from ..utils import find_xpath_attr, compat_str
class NBCIE(InfoExtractor):
_VALID_URL = r'http://www\.nbc\.com/[^/]+/video/[^/]+/(?P<id>n?\d+)'
_TEST = {
'url': 'http://www.nbc.com/chicago-fire/video/i-am-a-firefighter/2734188',
'md5': '54d0fbc33e0b853a65d7b4de5c06d64e',
'info_dict': {
'id': 'u1RInQZRN7QJ',
'ext': 'flv',
'title': 'I Am a Firefighter',
'description': 'An emergency puts Dawson\'sf irefighter skills to the ultimate test in this four-part digital series.',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id)
theplatform_url = self._search_regex('class="video-player video-player-full" data-mpx-url="(.*?)"', webpage, 'theplatform url')
if theplatform_url.startswith('//'):
theplatform_url = 'http:' + theplatform_url
return self.url_result(theplatform_url)
class NBCNewsIE(InfoExtractor):
_VALID_URL = r'https?://www\.nbcnews\.com/video/.+?/(?P<id>\d+)'
+2
View File
@@ -39,6 +39,8 @@ class TestURLIE(InfoExtractor):
('Found multiple matching extractors: %s' %
' '.join(ie.IE_NAME for ie in matching_extractors)),
expected=True)
else:
extractor = matching_extractors[0]
num_str = mobj.group('num')
num = int(num_str) if num_str else 0
+10 -4
View File
@@ -13,7 +13,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language
class ThePlatformIE(InfoExtractor):
_VALID_URL = r'''(?x)
(?:https?://(?:link|player)\.theplatform\.com/[sp]/[^/]+/
(?P<config>[^/\?]+/(?:swf|config)/select/)?
(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/)?
|theplatform:)(?P<id>[^/\?&]+)'''
_TEST = {
@@ -54,10 +54,15 @@ class ThePlatformIE(InfoExtractor):
f4m_node = body.find(_x('smil:seq/smil:video'))
if f4m_node is not None:
f4m_url = f4m_node.attrib['src']
if 'manifest.f4m?' not in f4m_url:
f4m_url += '?'
# the parameters are from syfy.com, other sites may use others,
# they also work for nbc.com
f4m_url += '&g=UXWGVKRWHFSP&hdcore=3.0.3'
formats = [{
'ext': 'flv',
# the parameters are from syfy.com, other sites may use others
'url': f4m_node.attrib['src'] + '?g=UXWGVKRWHFSP&hdcore=3.0.3',
'url': f4m_url,
}]
else:
base_url = head.find(_x('smil:meta')).attrib['base']
@@ -95,9 +100,10 @@ class ThePlatformIE(InfoExtractor):
if mobj.group('config'):
config_url = url+ '&form=json'
config_url = config_url.replace('swf/', 'config/')
config_url = config_url.replace('onsite/', 'onsite/config/')
config_json = self._download_webpage(config_url, video_id, u'Downloading config')
config = json.loads(config_json)
smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4'
smil_url = config['releaseUrl'] + '&format=SMIL&formats=MPEG4&manifest=f4m'
else:
smil_url = ('http://link.theplatform.com/s/dJ5BDC/{0}/meta.smil?'
'format=smil&mbr=true'.format(video_id))
+54 -3
View File
@@ -24,9 +24,10 @@ class VevoIE(InfoExtractor):
(?P<id>[^&?#]+)'''
_TESTS = [{
'url': 'http://www.vevo.com/watch/hurts/somebody-to-die-for/GB1101300280',
'file': 'GB1101300280.mp4',
"md5": "06bea460acb744eab74a9d7dcb4bfd61",
'info_dict': {
'id': 'GB1101300280',
'ext': 'mp4',
"upload_date": "20130624",
"uploader": "Hurts",
"title": "Somebody to Die For",
@@ -34,6 +35,33 @@ class VevoIE(InfoExtractor):
"width": 1920,
"height": 1080,
}
}, {
'note': 'v3 SMIL format',
'url': 'http://www.vevo.com/watch/cassadee-pope/i-wish-i-could-break-your-heart/USUV71302923',
'md5': '893ec0e0d4426a1d96c01de8f2bdff58',
'info_dict': {
'id': 'USUV71302923',
'ext': 'mp4',
'upload_date': '20140219',
'uploader': 'Cassadee Pope',
'title': 'I Wish I Could Break Your Heart',
'duration': 226.101,
'age_limit': 0,
}
}, {
'note': 'Age-limited video',
'url': 'https://www.vevo.com/watch/justin-timberlake/tunnel-vision-explicit/USRV81300282',
'info_dict': {
'id': 'USRV81300282',
'ext': 'mp4',
'age_limit': 18,
'title': 'Tunnel Vision (Explicit)',
'uploader': 'Justin Timberlake',
'upload_date': '20130704',
},
'params': {
'skip_download': 'true',
}
}]
_SMIL_BASE_URL = 'http://smil.lvl3.vevo.com/'
@@ -105,9 +133,31 @@ class VevoIE(InfoExtractor):
video_info = self._download_json(json_url, video_id)['video']
formats = self._formats_from_json(video_info)
is_explicit = video_info.get('isExplicit')
if is_explicit is True:
age_limit = 18
elif is_explicit is False:
age_limit = 0
else:
age_limit = None
# Download SMIL
smil_blocks = sorted((
f for f in video_info['videoVersions']
if f['sourceType'] == 13),
key=lambda f: f['version'])
smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
self._SMIL_BASE_URL, video_id, video_id.lower())
if smil_blocks:
smil_url_m = self._search_regex(
r'url="([^"]+)"', smil_blocks[-1]['data'], 'SMIL URL',
fatal=False)
if smil_url_m is not None:
smil_url = smil_url_m
try:
smil_url = '%s/Video/V2/VFILE/%s/%sr.smil' % (
self._SMIL_BASE_URL, video_id, video_id.lower())
smil_xml = self._download_webpage(smil_url, video_id,
'Downloading SMIL info')
formats.extend(self._formats_from_smil(smil_xml))
@@ -128,4 +178,5 @@ class VevoIE(InfoExtractor):
'upload_date': upload_date.strftime('%Y%m%d'),
'uploader': video_info['mainArtists'][0]['artistName'],
'duration': video_info['duration'],
'age_limit': age_limit,
}
+2 -2
View File
@@ -199,9 +199,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
'135': {'ext': 'mp4', 'height': 480, 'resolution': '480p', 'format_note': 'DASH video', 'preference': -40},
'136': {'ext': 'mp4', 'height': 720, 'resolution': '720p', 'format_note': 'DASH video', 'preference': -40},
'137': {'ext': 'mp4', 'height': 1080, 'resolution': '1080p', 'format_note': 'DASH video', 'preference': -40},
'138': {'ext': 'mp4', 'height': 1081, 'resolution': '>1080p', 'format_note': 'DASH video', 'preference': -40},
'138': {'ext': 'mp4', 'height': 2160, 'resolution': '2160p', 'format_note': 'DASH video', 'preference': -40},
'160': {'ext': 'mp4', 'height': 192, 'resolution': '192p', 'format_note': 'DASH video', 'preference': -40},
'264': {'ext': 'mp4', 'height': 1080, 'resolution': '1080p', 'format_note': 'DASH video', 'preference': -40},
'264': {'ext': 'mp4', 'height': 1440, 'resolution': '1440p', 'format_note': 'DASH video', 'preference': -40},
# Dash mp4 audio
'139': {'ext': 'm4a', 'format_note': 'DASH audio', 'vcodec': 'none', 'abr': 48, 'preference': -50},
+1 -1
View File
@@ -1,2 +1,2 @@
__version__ = '2014.02.25'
__version__ = '2014.02.26'