Merge branch 'master' of https://github.com/rg3/youtube-dl
This commit is contained in:
Gilles Habran
commit
8e36f9baf4
@ -698,6 +698,10 @@ YouTube changed their playlist format in March 2014 and later on, so you'll need
|
||||
|
||||
If you have installed youtube-dl with a package manager, pip, setup.py or a tarball, please use that to update. Note that Ubuntu packages do not seem to get updated anymore. Since we are not affiliated with Ubuntu, there is little we can do. Feel free to [report bugs](https://bugs.launchpad.net/ubuntu/+source/youtube-dl/+filebug) to the [Ubuntu packaging guys](mailto:ubuntu-motu@lists.ubuntu.com?subject=outdated%20version%20of%20youtube-dl) - all they have to do is update the package to a somewhat recent version. See above for a way to update.
|
||||
|
||||
### I'm getting an error when trying to use output template: `error: using output template conflicts with using title, video ID or auto number`
|
||||
|
||||
Make sure you are not using `-o` with any of these options `-t`, `--title`, `--id`, `-A` or `--auto-number` set in command line or in a configuration file. Remove the latter if any.
|
||||
|
||||
### Do I always have to pass `-citw`?
|
||||
|
||||
By default, youtube-dl intends to have the best options (incidentally, if you have a convincing case that these should be different, [please file an issue where you explain that](https://yt-dl.org/bug)). Therefore, it is unnecessary and sometimes harmful to copy long option strings from webpages. In particular, the only option out of `-citw` that is regularly useful is `-i`.
|
||||
@ -718,7 +722,7 @@ Videos or video formats streamed via RTMP protocol can only be downloaded when [
|
||||
|
||||
### I have downloaded a video but how can I play it?
|
||||
|
||||
Once the video is fully downloaded, use any video player, such as [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
|
||||
Once the video is fully downloaded, use any video player, such as [mpv](https://mpv.io/), [vlc](http://www.videolan.org) or [mplayer](http://www.mplayerhq.hu/).
|
||||
|
||||
### I extracted a video URL with `-g`, but it does not play on another machine / in my webbrowser.
|
||||
|
||||
|
||||
@ -63,7 +63,7 @@ class ArteTvIE(InfoExtractor):
|
||||
|
||||
class ArteTVPlus7IE(InfoExtractor):
|
||||
IE_NAME = 'arte.tv:+7'
|
||||
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&+])'
|
||||
_VALID_URL = r'https?://(?:www\.)?arte\.tv/guide/(?P<lang>fr|de|en|es)/(?:(?:sendungen|emissions|embed)/)?(?P<id>[^/]+)/(?P<name>[^/?#&]+)'
|
||||
|
||||
@classmethod
|
||||
def _extract_url_info(cls, url):
|
||||
|
||||
@ -19,7 +19,7 @@ from ..utils import (
|
||||
class CloudyIE(InfoExtractor):
|
||||
_IE_DESC = 'cloudy.ec and videoraj.ch'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.ch)/
|
||||
https?://(?:www\.)?(?P<host>cloudy\.ec|videoraj\.(?:ch|to))/
|
||||
(?:v/|embed\.php\?id=)
|
||||
(?P<id>[A-Za-z0-9]+)
|
||||
'''
|
||||
@ -37,7 +37,7 @@ class CloudyIE(InfoExtractor):
|
||||
}
|
||||
},
|
||||
{
|
||||
'url': 'http://www.videoraj.ch/v/47f399fd8bb60',
|
||||
'url': 'http://www.videoraj.to/v/47f399fd8bb60',
|
||||
'md5': '7d0f8799d91efd4eda26587421c3c3b0',
|
||||
'info_dict': {
|
||||
'id': '47f399fd8bb60',
|
||||
|
||||
@ -1061,7 +1061,7 @@ class InfoExtractor(object):
|
||||
def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
|
||||
entry_protocol='m3u8', preference=None,
|
||||
m3u8_id=None, note=None, errnote=None,
|
||||
fatal=True):
|
||||
fatal=True, live=False):
|
||||
|
||||
formats = [{
|
||||
'format_id': '-'.join(filter(None, [m3u8_id, 'meta'])),
|
||||
@ -1139,7 +1139,11 @@ class InfoExtractor(object):
|
||||
if m3u8_id:
|
||||
format_id.append(m3u8_id)
|
||||
last_media_name = last_media.get('NAME') if last_media and last_media.get('TYPE') != 'SUBTITLES' else None
|
||||
format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
|
||||
# Bandwidth of live streams may differ over time thus making
|
||||
# format_id unpredictable. So it's better to keep provided
|
||||
# format_id intact.
|
||||
if last_media_name and not live:
|
||||
format_id.append(last_media_name if last_media_name else '%d' % (tbr if tbr else len(formats)))
|
||||
f = {
|
||||
'format_id': '-'.join(format_id),
|
||||
'url': format_url(line.strip()),
|
||||
|
||||
@ -11,7 +11,6 @@ from math import pow, sqrt, floor
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_etree_fromstring,
|
||||
compat_urllib_parse_unquote,
|
||||
compat_urllib_parse_urlencode,
|
||||
compat_urllib_request,
|
||||
compat_urlparse,
|
||||
@ -27,6 +26,7 @@ from ..utils import (
|
||||
unified_strdate,
|
||||
urlencode_postdata,
|
||||
xpath_text,
|
||||
extract_attributes,
|
||||
)
|
||||
from ..aes import (
|
||||
aes_cbc_decrypt,
|
||||
@ -306,28 +306,33 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
||||
r'<a[^>]+href="/publisher/[^"]+"[^>]*>([^<]+)</a>', webpage,
|
||||
'video_uploader', fatal=False)
|
||||
|
||||
playerdata_url = compat_urllib_parse_unquote(self._html_search_regex(r'"config_url":"([^"]+)', webpage, 'playerdata_url'))
|
||||
playerdata_req = sanitized_Request(playerdata_url)
|
||||
playerdata_req.data = urlencode_postdata({'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)
|
||||
|
||||
available_fmts = []
|
||||
for a, fmt in re.findall(r'(<a[^>]+token="showmedia\.([0-9]{3,4})p"[^>]+>.*?</a>)', webpage):
|
||||
attrs = extract_attributes(a)
|
||||
href = attrs.get('href')
|
||||
if href and '/freetrial' in href:
|
||||
continue
|
||||
available_fmts.append(fmt)
|
||||
if not available_fmts:
|
||||
available_fmts = re.findall(r'token="showmedia\.([0-9]{3,4})p"', webpage)
|
||||
video_encode_ids = []
|
||||
formats = []
|
||||
for fmt in re.findall(r'showmedia\.([0-9]{3,4})p', webpage):
|
||||
for fmt in available_fmts:
|
||||
stream_quality, stream_format = self._FORMAT_IDS[fmt]
|
||||
video_format = fmt + 'p'
|
||||
streamdata_req = sanitized_Request(
|
||||
'http://www.crunchyroll.com/xml/?req=RpcApiVideoPlayer_GetStandardConfig&media_id=%s&video_format=%s&video_quality=%s'
|
||||
% (stream_id, stream_format, stream_quality),
|
||||
% (video_id, stream_format, stream_quality),
|
||||
compat_urllib_parse_urlencode({'current_page': url}).encode('utf-8'))
|
||||
streamdata_req.add_header('Content-Type', 'application/x-www-form-urlencoded')
|
||||
streamdata = self._download_xml(
|
||||
streamdata_req, video_id,
|
||||
note='Downloading media info for %s' % video_format)
|
||||
stream_info = streamdata.find('./{default}preload/stream_info')
|
||||
video_encode_id = xpath_text(stream_info, './video_encode_id')
|
||||
if video_encode_id in video_encode_ids:
|
||||
continue
|
||||
video_encode_ids.append(video_encode_id)
|
||||
video_url = xpath_text(stream_info, './host')
|
||||
video_play_path = xpath_text(stream_info, './file')
|
||||
if not video_url or not video_play_path:
|
||||
@ -360,15 +365,25 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
|
||||
})
|
||||
formats.append(format_info)
|
||||
|
||||
metadata = self._download_xml(
|
||||
'http://www.crunchyroll.com/xml', video_id,
|
||||
note='Downloading media info', query={
|
||||
'req': 'RpcApiVideoPlayer_GetMediaMetadata',
|
||||
'media_id': video_id,
|
||||
})
|
||||
|
||||
subtitles = self.extract_subtitles(video_id, webpage)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': video_title,
|
||||
'description': video_description,
|
||||
'thumbnail': video_thumbnail,
|
||||
'thumbnail': xpath_text(metadata, 'episode_image_url'),
|
||||
'uploader': video_uploader,
|
||||
'upload_date': video_upload_date,
|
||||
'series': xpath_text(metadata, 'series_title'),
|
||||
'episode': xpath_text(metadata, 'episode_title'),
|
||||
'episode_number': int_or_none(xpath_text(metadata, 'episode_number')),
|
||||
'subtitles': subtitles,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -9,7 +9,7 @@ from ..utils import (
|
||||
|
||||
|
||||
class CWTVIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/shows/(?:[^/]+/){2}\?play=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
|
||||
_VALID_URL = r'https?://(?:www\.)?cw(?:tv|seed)\.com/(?:shows/)?(?:[^/]+/){2}\?.*\bplay=(?P<id>[a-z0-9]{8}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{4}-[a-z0-9]{12})'
|
||||
_TESTS = [{
|
||||
'url': 'http://cwtv.com/shows/arrow/legends-of-yesterday/?play=6b15e985-9345-4f60-baf8-56e96be57c63',
|
||||
'info_dict': {
|
||||
@ -48,6 +48,9 @@ class CWTVIE(InfoExtractor):
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://cwtv.com/thecw/chroniclesofcisco/?play=8adebe35-f447-465f-ab52-e863506ff6d6',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -400,7 +400,6 @@ from .macgamestore import MacGameStoreIE
|
||||
from .mailru import MailRuIE
|
||||
from .makerschannel import MakersChannelIE
|
||||
from .makertv import MakerTVIE
|
||||
from .malemotion import MalemotionIE
|
||||
from .matchtv import MatchTVIE
|
||||
from .mdr import MDRIE
|
||||
from .metacafe import MetacafeIE
|
||||
@ -439,7 +438,7 @@ from .mtv import (
|
||||
)
|
||||
from .muenchentv import MuenchenTVIE
|
||||
from .musicplayon import MusicPlayOnIE
|
||||
from .mwave import MwaveIE
|
||||
from .mwave import MwaveIE, MwaveMeetGreetIE
|
||||
from .myspace import MySpaceIE, MySpaceAlbumIE
|
||||
from .myspass import MySpassIE
|
||||
from .myvi import MyviIE
|
||||
@ -658,7 +657,6 @@ from .screenwavemedia import ScreenwaveMediaIE, TeamFourIE
|
||||
from .senateisvp import SenateISVPIE
|
||||
from .servingsys import ServingSysIE
|
||||
from .sexu import SexuIE
|
||||
from .sexykarma import SexyKarmaIE
|
||||
from .shahid import ShahidIE
|
||||
from .shared import SharedIE
|
||||
from .sharesix import ShareSixIE
|
||||
@ -675,10 +673,6 @@ from .smotri import (
|
||||
SmotriUserIE,
|
||||
SmotriBroadcastIE,
|
||||
)
|
||||
from .snagfilms import (
|
||||
SnagFilmsIE,
|
||||
SnagFilmsEmbedIE,
|
||||
)
|
||||
from .snotr import SnotrIE
|
||||
from .sohu import SohuIE
|
||||
from .soundcloud import (
|
||||
@ -881,6 +875,10 @@ from .vidme import (
|
||||
)
|
||||
from .vidzi import VidziIE
|
||||
from .vier import VierIE, VierVideosIE
|
||||
from .viewlift import (
|
||||
ViewLiftIE,
|
||||
ViewLiftEmbedIE,
|
||||
)
|
||||
from .viewster import ViewsterIE
|
||||
from .viidea import ViideaIE
|
||||
from .vimeo import (
|
||||
@ -919,6 +917,7 @@ from .vulture import VultureIE
|
||||
from .walla import WallaIE
|
||||
from .washingtonpost import WashingtonPostIE
|
||||
from .wat import WatIE
|
||||
from .watchindianporn import WatchIndianPornIE
|
||||
from .wdr import (
|
||||
WDRIE,
|
||||
WDRMobileIE,
|
||||
|
||||
@ -51,7 +51,7 @@ from .tnaflix import TNAFlixNetworkEmbedIE
|
||||
from .vimeo import VimeoIE
|
||||
from .dailymotion import DailymotionCloudIE
|
||||
from .onionstudios import OnionStudiosIE
|
||||
from .snagfilms import SnagFilmsEmbedIE
|
||||
from .viewlift import ViewLiftEmbedIE
|
||||
from .screenwavemedia import ScreenwaveMediaIE
|
||||
from .mtv import MTVServicesEmbeddedIE
|
||||
from .pladform import PladformIE
|
||||
@ -1924,10 +1924,10 @@ class GenericIE(InfoExtractor):
|
||||
if onionstudios_url:
|
||||
return self.url_result(onionstudios_url)
|
||||
|
||||
# Look for SnagFilms embeds
|
||||
snagfilms_url = SnagFilmsEmbedIE._extract_url(webpage)
|
||||
if snagfilms_url:
|
||||
return self.url_result(snagfilms_url)
|
||||
# Look for ViewLift embeds
|
||||
viewlift_url = ViewLiftEmbedIE._extract_url(webpage)
|
||||
if viewlift_url:
|
||||
return self.url_result(viewlift_url)
|
||||
|
||||
# Look for JWPlatform embeds
|
||||
jwplatform_url = JWPlatformIE._extract_url(webpage)
|
||||
|
||||
@ -1,46 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..compat import compat_urllib_parse_unquote
|
||||
|
||||
|
||||
class MalemotionIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://malemotion\.com/video/(.+?)\.(?P<id>.+?)(#|$)'
|
||||
_TEST = {
|
||||
'url': 'http://malemotion.com/video/bete-de-concours.ltc',
|
||||
'md5': '3013e53a0afbde2878bc39998c33e8a5',
|
||||
'info_dict': {
|
||||
'id': 'ltc',
|
||||
'ext': 'mp4',
|
||||
'title': 'Bête de Concours',
|
||||
'age_limit': 18,
|
||||
},
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
|
||||
video_url = compat_urllib_parse_unquote(self._search_regex(
|
||||
r'<source type="video/mp4" src="(.+?)"', webpage, 'video URL'))
|
||||
video_title = self._html_search_regex(
|
||||
r'<title>(.*?)</title', webpage, 'title')
|
||||
video_thumbnail = self._search_regex(
|
||||
r'<video .+?poster="(.+?)"', webpage, 'thumbnail', fatal=False)
|
||||
|
||||
formats = [{
|
||||
'url': video_url,
|
||||
'ext': 'mp4',
|
||||
'format_id': 'mp4',
|
||||
'preference': 1,
|
||||
}]
|
||||
self._sort_formats(formats)
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
'title': video_title,
|
||||
'thumbnail': video_thumbnail,
|
||||
'age_limit': 18,
|
||||
}
|
||||
@ -10,6 +10,7 @@ from ..utils import (
|
||||
|
||||
class MwaveIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://mwave\.interest\.me/mnettv/videodetail\.m\?searchVideoDetailVO\.clip_id=(?P<id>[0-9]+)'
|
||||
_URL_TEMPLATE = 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=%s'
|
||||
_TEST = {
|
||||
'url': 'http://mwave.interest.me/mnettv/videodetail.m?searchVideoDetailVO.clip_id=168859',
|
||||
# md5 is unstable
|
||||
@ -56,3 +57,28 @@ class MwaveIE(InfoExtractor):
|
||||
'view_count': int_or_none(vod_info.get('hit')),
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
|
||||
class MwaveMeetGreetIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://mwave\.interest\.me/meetgreet/view/(?P<id>\d+)'
|
||||
_TEST = {
|
||||
'url': 'http://mwave.interest.me/meetgreet/view/256',
|
||||
'info_dict': {
|
||||
'id': '173294',
|
||||
'ext': 'flv',
|
||||
'title': '[MEET&GREET] Park BoRam',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'uploader': 'Mwave',
|
||||
'duration': 3634,
|
||||
'view_count': int,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
clip_id = self._html_search_regex(
|
||||
r'<iframe[^>]+src="/mnettv/ifr_clip\.m\?searchVideoDetailVO\.clip_id=(\d+)',
|
||||
webpage, 'clip ID')
|
||||
clip_url = MwaveIE._URL_TEMPLATE % clip_id
|
||||
return self.url_result(clip_url, 'Mwave', clip_id)
|
||||
|
||||
@ -5,8 +5,6 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
parse_duration,
|
||||
sanitized_Request,
|
||||
unified_strdate,
|
||||
)
|
||||
|
||||
|
||||
@ -20,7 +18,6 @@ class NuvidIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'title': 'Horny babes show their awesome bodeis and',
|
||||
'duration': 129,
|
||||
'upload_date': '20140508',
|
||||
'age_limit': 18,
|
||||
}
|
||||
}
|
||||
@ -28,28 +25,31 @@ class NuvidIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
|
||||
formats = []
|
||||
page_url = 'http://m.nuvid.com/video/%s' % video_id
|
||||
webpage = self._download_webpage(
|
||||
page_url, video_id, 'Downloading video page')
|
||||
# When dwnld_speed exists and has a value larger than the MP4 file's
|
||||
# bitrate, Nuvid returns the MP4 URL
|
||||
# It's unit is 100bytes/millisecond, see mobile-nuvid-min.js for the algorithm
|
||||
self._set_cookie('nuvid.com', 'dwnld_speed', '10.0')
|
||||
mp4_webpage = self._download_webpage(
|
||||
page_url, video_id, 'Downloading video page for MP4 format')
|
||||
|
||||
for dwnld_speed, format_id in [(0, '3gp'), (5, 'mp4')]:
|
||||
request = sanitized_Request(
|
||||
'http://m.nuvid.com/play/%s' % video_id)
|
||||
request.add_header('Cookie', 'skip_download_page=1; dwnld_speed=%d; adv_show=1' % dwnld_speed)
|
||||
webpage = self._download_webpage(
|
||||
request, video_id, 'Downloading %s page' % format_id)
|
||||
video_url = self._html_search_regex(
|
||||
r'<a\s+href="([^"]+)"\s+class="b_link">', webpage, '%s video URL' % format_id, fatal=False)
|
||||
if not video_url:
|
||||
continue
|
||||
html5_video_re = r'(?s)<(?:video|audio)[^<]*(?:>.*?<source[^>]*)?\s+src=["\'](.*?)["\']',
|
||||
video_url = self._html_search_regex(html5_video_re, webpage, video_id)
|
||||
mp4_video_url = self._html_search_regex(html5_video_re, mp4_webpage, video_id)
|
||||
formats = [{
|
||||
'url': video_url,
|
||||
}]
|
||||
if mp4_video_url != video_url:
|
||||
formats.append({
|
||||
'url': video_url,
|
||||
'format_id': format_id,
|
||||
'url': mp4_video_url,
|
||||
})
|
||||
|
||||
webpage = self._download_webpage(
|
||||
'http://m.nuvid.com/video/%s' % video_id, video_id, 'Downloading video page')
|
||||
title = self._html_search_regex(
|
||||
[r'<span title="([^"]+)">',
|
||||
r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>'], webpage, 'title').strip()
|
||||
r'<div class="thumb-holder video">\s*<h5[^>]*>([^<]+)</h5>',
|
||||
r'<span[^>]+class="title_thumb">([^<]+)</span>'], webpage, 'title').strip()
|
||||
thumbnails = [
|
||||
{
|
||||
'url': thumb_url,
|
||||
@ -57,9 +57,8 @@ class NuvidIE(InfoExtractor):
|
||||
]
|
||||
thumbnail = thumbnails[0]['url'] if thumbnails else None
|
||||
duration = parse_duration(self._html_search_regex(
|
||||
r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})', webpage, 'duration', fatal=False))
|
||||
upload_date = unified_strdate(self._html_search_regex(
|
||||
r'<i class="fa fa-user"></i>\s*(\d{4}-\d{2}-\d{2})', webpage, 'upload date', fatal=False))
|
||||
[r'<i class="fa fa-clock-o"></i>\s*(\d{2}:\d{2})',
|
||||
r'<span[^>]+class="view_time">([^<]+)</span>'], webpage, 'duration', fatal=False))
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
@ -67,7 +66,6 @@ class NuvidIE(InfoExtractor):
|
||||
'thumbnails': thumbnails,
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'upload_date': upload_date,
|
||||
'age_limit': 18,
|
||||
'formats': formats,
|
||||
}
|
||||
|
||||
@ -96,6 +96,8 @@ class OoyalaIE(OoyalaBaseIE):
|
||||
'description': 'How badly damaged does a drive have to be to defeat Russell and his crew? Apparently, smashed to bits.',
|
||||
'duration': 853.386,
|
||||
},
|
||||
# The video in the original webpage now uses PlayWire
|
||||
'skip': 'Ooyala said: movie expired',
|
||||
}, {
|
||||
# Only available for ipad
|
||||
'url': 'http://player.ooyala.com/player.js?embedCode=x1b3lqZDq9y_7kMyC2Op5qo-p077tXD0',
|
||||
|
||||
@ -185,6 +185,7 @@ class ORFFM4IE(InfoExtractor):
|
||||
'timestamp': 1452456073,
|
||||
'upload_date': '20160110',
|
||||
},
|
||||
'skip': 'Live streams on FM4 got deleted soon',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -18,6 +18,7 @@ class SciVeeIE(InfoExtractor):
|
||||
'title': 'Adam Arkin at the 2014 DOE JGI Genomics of Energy & Environment Meeting',
|
||||
'description': 'md5:81f1710638e11a481358fab1b11059d7',
|
||||
},
|
||||
'skip': 'Not accessible from Travis CI server',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -159,11 +159,11 @@ class ThePlatformIE(ThePlatformBaseIE):
|
||||
def str_to_hex(str):
|
||||
return binascii.b2a_hex(str.encode('ascii')).decode('ascii')
|
||||
|
||||
def hex_to_str(hex):
|
||||
return binascii.a2b_hex(hex)
|
||||
def hex_to_bytes(hex):
|
||||
return binascii.a2b_hex(hex.encode('ascii'))
|
||||
|
||||
relative_path = re.match(r'https?://link.theplatform.com/s/([^?]+)', url).group(1)
|
||||
clear_text = hex_to_str(flags + expiration_date + str_to_hex(relative_path))
|
||||
clear_text = hex_to_bytes(flags + expiration_date + str_to_hex(relative_path))
|
||||
checksum = hmac.new(sig_key.encode('ascii'), clear_text, hashlib.sha1).hexdigest()
|
||||
sig = flags + expiration_date + checksum + str_to_hex(sig_secret)
|
||||
return '%s&sig=%s' % (url, sig)
|
||||
|
||||
@ -32,7 +32,22 @@ class TwentyMinutenIE(InfoExtractor):
|
||||
'title': '«Wir müssen mutig nach vorne schauen»',
|
||||
'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.',
|
||||
'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg'
|
||||
}
|
||||
},
|
||||
'skip': '"This video is no longer available" is shown both on the web page and in the downloaded file.',
|
||||
}, {
|
||||
# YouTube embed
|
||||
'url': 'http://www.20min.ch/ro/sports/football/story/Il-marque-une-bicyclette-de-plus-de-30-metres--21115184',
|
||||
'md5': 'cec64d59aa01c0ed9dbba9cf639dd82f',
|
||||
'info_dict': {
|
||||
'id': 'ivM7A7SpDOs',
|
||||
'ext': 'mp4',
|
||||
'title': 'GOLAZO DE CHILENA DE JAVI GÓMEZ, FINALISTA AL BALÓN DE CLM 2016',
|
||||
'description': 'md5:903c92fbf2b2f66c09de514bc25e9f5a',
|
||||
'upload_date': '20160424',
|
||||
'uploader': 'RTVCM Castilla-La Mancha',
|
||||
'uploader_id': 'RTVCM',
|
||||
},
|
||||
'add_ie': ['Youtube'],
|
||||
}, {
|
||||
'url': 'http://www.20min.ch/videotv/?cid=44&vid=468738',
|
||||
'only_matching': True,
|
||||
@ -48,6 +63,12 @@ class TwentyMinutenIE(InfoExtractor):
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
youtube_url = self._html_search_regex(
|
||||
r'<iframe[^>]+src="((?:https?:)?//www\.youtube\.com/embed/[^"]+)"',
|
||||
webpage, 'YouTube embed URL', default=None)
|
||||
if youtube_url is not None:
|
||||
return self.url_result(youtube_url, 'Youtube')
|
||||
|
||||
title = self._html_search_regex(
|
||||
r'<h1>.*?<span>(.+?)</span></h1>',
|
||||
webpage, 'title', default=None)
|
||||
|
||||
@ -13,8 +13,12 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class SnagFilmsEmbedIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:www|embed)\.)?snagfilms\.com/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})'
|
||||
class ViewLiftBaseIE(InfoExtractor):
|
||||
_DOMAINS_REGEX = '(?:snagfilms|snagxtreme|funnyforfree|kiddovid|winnersview|monumentalsportsnetwork|vayafilm)\.com|kesari\.tv'
|
||||
|
||||
|
||||
class ViewLiftEmbedIE(ViewLiftBaseIE):
|
||||
_VALID_URL = r'https?://(?:(?:www|embed)\.)?(?:%s)/embed/player\?.*\bfilmId=(?P<id>[\da-f-]{36})' % ViewLiftBaseIE._DOMAINS_REGEX
|
||||
_TESTS = [{
|
||||
'url': 'http://embed.snagfilms.com/embed/player?filmId=74849a00-85a9-11e1-9660-123139220831&w=500',
|
||||
'md5': '2924e9215c6eff7a55ed35b72276bd93',
|
||||
@ -40,7 +44,7 @@ class SnagFilmsEmbedIE(InfoExtractor):
|
||||
@staticmethod
|
||||
def _extract_url(webpage):
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?snagfilms\.com/embed/player.+?)\1',
|
||||
r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:embed\.)?(?:%s)/embed/player.+?)\1' % ViewLiftBaseIE._DOMAINS_REGEX,
|
||||
webpage)
|
||||
if mobj:
|
||||
return mobj.group('url')
|
||||
@ -55,6 +59,7 @@ class SnagFilmsEmbedIE(InfoExtractor):
|
||||
'Film %s is not playable in your area.' % video_id, expected=True)
|
||||
|
||||
formats = []
|
||||
has_bitrate = False
|
||||
for source in self._parse_json(js_to_json(self._search_regex(
|
||||
r'(?s)sources:\s*(\[.+?\]),', webpage, 'json')), video_id):
|
||||
file_ = source.get('file')
|
||||
@ -63,22 +68,25 @@ class SnagFilmsEmbedIE(InfoExtractor):
|
||||
type_ = source.get('type')
|
||||
ext = determine_ext(file_)
|
||||
format_id = source.get('label') or ext
|
||||
if all(v == 'm3u8' for v in (type_, ext)):
|
||||
if all(v == 'm3u8' or v == 'hls' for v in (type_, ext)):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
file_, video_id, 'mp4', m3u8_id='hls'))
|
||||
else:
|
||||
bitrate = int_or_none(self._search_regex(
|
||||
[r'(\d+)kbps', r'_\d{1,2}x\d{1,2}_(\d{3,})\.%s' % ext],
|
||||
file_, 'bitrate', default=None))
|
||||
if not has_bitrate and bitrate:
|
||||
has_bitrate = True
|
||||
height = int_or_none(self._search_regex(
|
||||
r'^(\d+)[pP]$', format_id, 'height', default=None))
|
||||
formats.append({
|
||||
'url': file_,
|
||||
'format_id': format_id,
|
||||
'format_id': 'http-%s%s' % (format_id, ('-%dk' % bitrate if bitrate else '')),
|
||||
'tbr': bitrate,
|
||||
'height': height,
|
||||
})
|
||||
self._sort_formats(formats)
|
||||
field_preference = None if has_bitrate else ('height', 'tbr', 'format_id')
|
||||
self._sort_formats(formats, field_preference)
|
||||
|
||||
title = self._search_regex(
|
||||
[r"title\s*:\s*'([^']+)'", r'<title>([^<]+)</title>'],
|
||||
@ -91,8 +99,8 @@ class SnagFilmsEmbedIE(InfoExtractor):
|
||||
}
|
||||
|
||||
|
||||
class SnagFilmsIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?snagfilms\.com/(?:films/title|show)/(?P<id>[^?#]+)'
|
||||
class ViewLiftIE(ViewLiftBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?P<domain>%s)/(?:films/title|show|(?:news/)?videos?)/(?P<id>[^?#]+)' % ViewLiftBaseIE._DOMAINS_REGEX
|
||||
_TESTS = [{
|
||||
'url': 'http://www.snagfilms.com/films/title/lost_for_life',
|
||||
'md5': '19844f897b35af219773fd63bdec2942',
|
||||
@ -127,10 +135,16 @@ class SnagFilmsIE(InfoExtractor):
|
||||
# Film is not available.
|
||||
'url': 'http://www.snagfilms.com/show/augie_alone/flirting',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.winnersview.com/videos/the-good-son',
|
||||
'only_matching': True,
|
||||
}, {
|
||||
'url': 'http://www.kesari.tv/news/video/1461919076414',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
domain, display_id = re.match(self._VALID_URL, url).groups()
|
||||
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
|
||||
@ -170,7 +184,7 @@ class SnagFilmsIE(InfoExtractor):
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': 'http://embed.snagfilms.com/embed/player?filmId=%s' % film_id,
|
||||
'url': 'http://%s/embed/player?filmId=%s' % (domain, film_id),
|
||||
'id': film_id,
|
||||
'display_id': display_id,
|
||||
'title': title,
|
||||
@ -178,4 +192,5 @@ class SnagFilmsIE(InfoExtractor):
|
||||
'thumbnail': thumbnail,
|
||||
'duration': duration,
|
||||
'categories': categories,
|
||||
'ie_key': 'ViewLiftEmbed',
|
||||
}
|
||||
@ -6,7 +6,6 @@ import re
|
||||
from .common import InfoExtractor
|
||||
from ..compat import (
|
||||
compat_HTTPError,
|
||||
compat_urllib_parse,
|
||||
compat_urllib_parse_unquote,
|
||||
)
|
||||
from ..utils import (
|
||||
@ -78,11 +77,11 @@ class ViewsterIE(InfoExtractor):
|
||||
|
||||
_ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01'
|
||||
|
||||
def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True):
|
||||
def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True, query={}):
|
||||
request = sanitized_Request(url)
|
||||
request.add_header('Accept', self._ACCEPT_HEADER)
|
||||
request.add_header('Auth-token', self._AUTH_TOKEN)
|
||||
return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal)
|
||||
return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal, query=query)
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
@ -117,57 +116,85 @@ class ViewsterIE(InfoExtractor):
|
||||
return self.playlist_result(entries, video_id, title, description)
|
||||
|
||||
formats = []
|
||||
manifest_url = None
|
||||
for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'):
|
||||
media = self._download_json(
|
||||
'https://public-api.viewster.com/movies/%s/video?mediaType=%s'
|
||||
% (entry_id, compat_urllib_parse.quote(media_type)),
|
||||
video_id, 'Downloading %s JSON' % media_type, fatal=False)
|
||||
if not media:
|
||||
continue
|
||||
video_url = media.get('Uri')
|
||||
if not video_url:
|
||||
continue
|
||||
ext = determine_ext(video_url)
|
||||
if ext == 'f4m':
|
||||
manifest_url = video_url
|
||||
video_url += '&' if '?' in video_url else '?'
|
||||
video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1'
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
video_url, video_id, f4m_id='hds'))
|
||||
elif ext == 'm3u8':
|
||||
manifest_url = video_url
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
video_url, video_id, 'mp4', m3u8_id='hls',
|
||||
fatal=False) # m3u8 sometimes fail
|
||||
if m3u8_formats:
|
||||
formats.extend(m3u8_formats)
|
||||
else:
|
||||
qualities_basename = self._search_regex(
|
||||
'/([^/]+)\.csmil/',
|
||||
manifest_url, 'qualities basename', default=None)
|
||||
if not qualities_basename:
|
||||
continue
|
||||
QUALITIES_RE = r'((,\d+k)+,?)'
|
||||
qualities = self._search_regex(
|
||||
QUALITIES_RE, qualities_basename,
|
||||
'qualities', default=None)
|
||||
if not qualities:
|
||||
continue
|
||||
qualities = qualities.strip(',').split(',')
|
||||
http_template = re.sub(QUALITIES_RE, r'%s', qualities_basename)
|
||||
http_url_basename = url_basename(video_url)
|
||||
for q in qualities:
|
||||
tbr = int_or_none(self._search_regex(
|
||||
r'(\d+)k', q, 'bitrate', default=None))
|
||||
formats.append({
|
||||
'url': video_url.replace(http_url_basename, http_template % q),
|
||||
'ext': 'mp4',
|
||||
'format_id': 'http' + ('-%d' % tbr if tbr else ''),
|
||||
'tbr': tbr,
|
||||
})
|
||||
for language_set in info.get('LanguageSets', []):
|
||||
manifest_url = None
|
||||
m3u8_formats = []
|
||||
audio = language_set.get('Audio') or ''
|
||||
subtitle = language_set.get('Subtitle') or ''
|
||||
base_format_id = audio
|
||||
if subtitle:
|
||||
base_format_id += '-%s' % subtitle
|
||||
|
||||
if not formats and not info.get('LanguageSets') and not info.get('VODSettings'):
|
||||
def concat(suffix, sep='-'):
|
||||
return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix
|
||||
|
||||
for media_type in ('application/f4m+xml', 'application/x-mpegURL', 'video/mp4'):
|
||||
media = self._download_json(
|
||||
'https://public-api.viewster.com/movies/%s/video' % entry_id,
|
||||
video_id, 'Downloading %s JSON' % concat(media_type, ' '), fatal=False, query={
|
||||
'mediaType': media_type,
|
||||
'language': audio,
|
||||
'subtitle': subtitle,
|
||||
})
|
||||
if not media:
|
||||
continue
|
||||
video_url = media.get('Uri')
|
||||
if not video_url:
|
||||
continue
|
||||
ext = determine_ext(video_url)
|
||||
if ext == 'f4m':
|
||||
manifest_url = video_url
|
||||
video_url += '&' if '?' in video_url else '?'
|
||||
video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1'
|
||||
formats.extend(self._extract_f4m_formats(
|
||||
video_url, video_id, f4m_id=concat('hds')))
|
||||
elif ext == 'm3u8':
|
||||
manifest_url = video_url
|
||||
m3u8_formats = self._extract_m3u8_formats(
|
||||
video_url, video_id, 'mp4', m3u8_id=concat('hls'),
|
||||
fatal=False) # m3u8 sometimes fail
|
||||
if m3u8_formats:
|
||||
formats.extend(m3u8_formats)
|
||||
else:
|
||||
qualities_basename = self._search_regex(
|
||||
'/([^/]+)\.csmil/',
|
||||
manifest_url, 'qualities basename', default=None)
|
||||
if not qualities_basename:
|
||||
continue
|
||||
QUALITIES_RE = r'((,\d+k)+,?)'
|
||||
qualities = self._search_regex(
|
||||
QUALITIES_RE, qualities_basename,
|
||||
'qualities', default=None)
|
||||
if not qualities:
|
||||
continue
|
||||
qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(',')))
|
||||
qualities.sort()
|
||||
http_template = re.sub(QUALITIES_RE, r'%dk', qualities_basename)
|
||||
http_url_basename = url_basename(video_url)
|
||||
if m3u8_formats:
|
||||
self._sort_formats(m3u8_formats)
|
||||
m3u8_formats = list(filter(
|
||||
lambda f: f.get('vcodec') != 'none' and f.get('resolution') != 'multiple',
|
||||
m3u8_formats))
|
||||
if len(qualities) == len(m3u8_formats):
|
||||
for q, m3u8_format in zip(qualities, m3u8_formats):
|
||||
f = m3u8_format.copy()
|
||||
f.update({
|
||||
'url': video_url.replace(http_url_basename, http_template % q),
|
||||
'format_id': f['format_id'].replace('hls', 'http'),
|
||||
'protocol': 'http',
|
||||
})
|
||||
formats.append(f)
|
||||
else:
|
||||
for q in qualities:
|
||||
formats.append({
|
||||
'url': video_url.replace(http_url_basename, http_template % q),
|
||||
'ext': 'mp4',
|
||||
'format_id': 'http-%d' % q,
|
||||
'tbr': q,
|
||||
})
|
||||
|
||||
if not formats and not info.get('VODSettings'):
|
||||
self.raise_geo_restricted()
|
||||
|
||||
self._sort_formats(formats)
|
||||
|
||||
@ -1,9 +1,13 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
from __future__ import division, unicode_literals
|
||||
|
||||
import re
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
dict_get,
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
)
|
||||
@ -31,16 +35,76 @@ class VLiveIE(InfoExtractor):
|
||||
webpage = self._download_webpage(
|
||||
'http://www.vlive.tv/video/%s' % video_id, video_id)
|
||||
|
||||
long_video_id = self._search_regex(
|
||||
r'vlive\.tv\.video\.ajax\.request\.handler\.init\(\s*"[0-9]+"\s*,\s*"[^"]*"\s*,\s*"([^"]+)"',
|
||||
webpage, 'long video id')
|
||||
# UTC+x - UTC+9 (KST)
|
||||
tz = time.altzone if time.localtime().tm_isdst == 1 else time.timezone
|
||||
tz_offset = -tz // 60 - 9 * 60
|
||||
self._set_cookie('vlive.tv', 'timezoneOffset', '%d' % tz_offset)
|
||||
|
||||
key = self._search_regex(
|
||||
r'vlive\.tv\.video\.ajax\.request\.handler\.init\(\s*"[0-9]+"\s*,\s*"[^"]*"\s*,\s*"[^"]+"\s*,\s*"([^"]+)"',
|
||||
webpage, 'key')
|
||||
status_params = self._download_json(
|
||||
'http://www.vlive.tv/video/status?videoSeq=%s' % video_id,
|
||||
video_id, 'Downloading JSON status',
|
||||
headers={'Referer': url})
|
||||
status = status_params.get('status')
|
||||
air_start = status_params.get('onAirStartAt', '')
|
||||
is_live = status_params.get('isLive')
|
||||
|
||||
video_params = self._search_regex(
|
||||
r'vlive\.tv\.video\.ajax\.request\.handler\.init\((.+)\)',
|
||||
webpage, 'video params')
|
||||
live_params, long_video_id, key = re.split(
|
||||
r'"\s*,\s*"', video_params)[1:4]
|
||||
|
||||
if status == 'LIVE_ON_AIR' or status == 'BIG_EVENT_ON_AIR':
|
||||
live_params = self._parse_json('"%s"' % live_params, video_id)
|
||||
live_params = self._parse_json(live_params, video_id)
|
||||
return self._live(video_id, webpage, live_params)
|
||||
elif status == 'VOD_ON_AIR' or status == 'BIG_EVENT_INTRO':
|
||||
if long_video_id and key:
|
||||
return self._replay(video_id, webpage, long_video_id, key)
|
||||
elif is_live:
|
||||
status = 'LIVE_END'
|
||||
else:
|
||||
status = 'COMING_SOON'
|
||||
|
||||
if status == 'LIVE_END':
|
||||
raise ExtractorError('Uploading for replay. Please wait...',
|
||||
expected=True)
|
||||
elif status == 'COMING_SOON':
|
||||
raise ExtractorError('Coming soon! %s' % air_start, expected=True)
|
||||
elif status == 'CANCELED':
|
||||
raise ExtractorError('We are sorry, '
|
||||
'but the live broadcast has been canceled.',
|
||||
expected=True)
|
||||
else:
|
||||
raise ExtractorError('Unknown status %s' % status)
|
||||
|
||||
def _get_common_fields(self, webpage):
|
||||
title = self._og_search_title(webpage)
|
||||
creator = self._html_search_regex(
|
||||
r'<div[^>]+class="info_area"[^>]*>\s*<a\s+[^>]*>([^<]+)',
|
||||
webpage, 'creator', fatal=False)
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
return {
|
||||
'title': title,
|
||||
'creator': creator,
|
||||
'thumbnail': thumbnail,
|
||||
}
|
||||
|
||||
def _live(self, video_id, webpage, live_params):
|
||||
formats = []
|
||||
for vid in live_params.get('resolutions', []):
|
||||
formats.extend(self._extract_m3u8_formats(
|
||||
vid['cdnUrl'], video_id, 'mp4',
|
||||
m3u8_id=vid.get('name'),
|
||||
fatal=False, live=True))
|
||||
self._sort_formats(formats)
|
||||
|
||||
return dict(self._get_common_fields(webpage),
|
||||
id=video_id,
|
||||
formats=formats,
|
||||
is_live=True)
|
||||
|
||||
def _replay(self, video_id, webpage, long_video_id, key):
|
||||
playinfo = self._download_json(
|
||||
'http://global.apis.naver.com/rmcnmv/rmcnmv/vod_play_videoInfo.json?%s'
|
||||
% compat_urllib_parse_urlencode({
|
||||
@ -62,11 +126,6 @@ class VLiveIE(InfoExtractor):
|
||||
} for vid in playinfo.get('videos', {}).get('list', []) if vid.get('source')]
|
||||
self._sort_formats(formats)
|
||||
|
||||
thumbnail = self._og_search_thumbnail(webpage)
|
||||
creator = self._html_search_regex(
|
||||
r'<div[^>]+class="info_area"[^>]*>\s*<a\s+[^>]*>([^<]+)',
|
||||
webpage, 'creator', fatal=False)
|
||||
|
||||
view_count = int_or_none(playinfo.get('meta', {}).get('count'))
|
||||
|
||||
subtitles = {}
|
||||
@ -77,12 +136,8 @@ class VLiveIE(InfoExtractor):
|
||||
'ext': 'vtt',
|
||||
'url': caption['source']}]
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'creator': creator,
|
||||
'thumbnail': thumbnail,
|
||||
'view_count': view_count,
|
||||
'formats': formats,
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
return dict(self._get_common_fields(webpage),
|
||||
id=video_id,
|
||||
formats=formats,
|
||||
view_count=view_count,
|
||||
subtitles=subtitles)
|
||||
|
||||
@ -11,61 +11,27 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class SexyKarmaIE(InfoExtractor):
|
||||
IE_DESC = 'Sexy Karma and Watch Indian Porn'
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:sexykarma\.com|watchindianporn\.net)/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.sexykarma.com/gonewild/video/taking-a-quick-pee-yHI70cOyIHt.html',
|
||||
'md5': 'b9798e7d1ef1765116a8f516c8091dbd',
|
||||
class WatchIndianPornIE(InfoExtractor):
|
||||
IE_DESC = 'Watch Indian Porn'
|
||||
_VALID_URL = r'https?://(?:www\.)?watchindianporn\.net/(?:[^/]+/)*video/(?P<display_id>[^/]+)-(?P<id>[a-zA-Z0-9]+)\.html'
|
||||
_TEST = {
|
||||
'url': 'http://www.watchindianporn.net/video/hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera-RZa2avywNPa.html',
|
||||
'md5': '249589a164dde236ec65832bfce17440',
|
||||
'info_dict': {
|
||||
'id': 'yHI70cOyIHt',
|
||||
'display_id': 'taking-a-quick-pee',
|
||||
'id': 'RZa2avywNPa',
|
||||
'display_id': 'hot-milf-from-kerala-shows-off-her-gorgeous-large-breasts-on-camera',
|
||||
'ext': 'mp4',
|
||||
'title': 'Taking a quick pee.',
|
||||
'title': 'Hot milf from kerala shows off her gorgeous large breasts on camera',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'uploader': 'wildginger7',
|
||||
'upload_date': '20141008',
|
||||
'duration': 22,
|
||||
'uploader': 'LoveJay',
|
||||
'upload_date': '20160428',
|
||||
'duration': 226,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'categories': list,
|
||||
'age_limit': 18,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.sexykarma.com/gonewild/video/pot-pixie-tribute-8Id6EZPbuHf.html',
|
||||
'md5': 'dd216c68d29b49b12842b9babe762a5d',
|
||||
'info_dict': {
|
||||
'id': '8Id6EZPbuHf',
|
||||
'display_id': 'pot-pixie-tribute',
|
||||
'ext': 'mp4',
|
||||
'title': 'pot_pixie tribute',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'uploader': 'banffite',
|
||||
'upload_date': '20141013',
|
||||
'duration': 16,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'categories': list,
|
||||
'age_limit': 18,
|
||||
}
|
||||
}, {
|
||||
'url': 'http://www.watchindianporn.net/video/desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number-dW2mtctxJfs.html',
|
||||
'md5': '9afb80675550406ed9a63ac2819ef69d',
|
||||
'info_dict': {
|
||||
'id': 'dW2mtctxJfs',
|
||||
'display_id': 'desi-dancer-namrata-stripping-completely-nude-and-dancing-on-a-hot-number',
|
||||
'ext': 'mp4',
|
||||
'title': 'Desi dancer namrata stripping completely nude and dancing on a hot number',
|
||||
'thumbnail': 're:^https?://.*\.jpg$',
|
||||
'uploader': 'Don',
|
||||
'upload_date': '20140213',
|
||||
'duration': 83,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
'categories': list,
|
||||
'age_limit': 18,
|
||||
}
|
||||
}]
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
@ -109,6 +75,9 @@ class SexyKarmaIE(InfoExtractor):
|
||||
'id': video_id,
|
||||
'display_id': display_id,
|
||||
'url': video_url,
|
||||
'http_headers': {
|
||||
'Referer': url,
|
||||
},
|
||||
'title': title,
|
||||
'thumbnail': thumbnail,
|
||||
'uploader': uploader,
|
||||
@ -18,9 +18,23 @@ from ..utils import (
|
||||
class YandexMusicBaseIE(InfoExtractor):
|
||||
@staticmethod
|
||||
def _handle_error(response):
|
||||
error = response.get('error')
|
||||
if error:
|
||||
raise ExtractorError(error, expected=True)
|
||||
if isinstance(response, dict):
|
||||
error = response.get('error')
|
||||
if error:
|
||||
raise ExtractorError(error, expected=True)
|
||||
|
||||
def _download_webpage(self, *args, **kwargs):
|
||||
webpage = super(YandexMusicBaseIE, self)._download_webpage(*args, **kwargs)
|
||||
if 'Нам очень жаль, но запросы, поступившие с вашего IP-адреса, похожи на автоматические.' in webpage:
|
||||
raise ExtractorError(
|
||||
'YandexMusic has considered youtube-dl requests automated and '
|
||||
'asks you to solve a CAPTCHA. You can either wait for some '
|
||||
'time until unblocked and optionally use --sleep-interval '
|
||||
'in future or alternatively you can go to https://music.yandex.ru/ '
|
||||
'solve CAPTCHA, then export cookies and pass cookie file to '
|
||||
'youtube-dl with --cookies',
|
||||
expected=True)
|
||||
return webpage
|
||||
|
||||
def _download_json(self, *args, **kwargs):
|
||||
response = super(YandexMusicBaseIE, self)._download_json(*args, **kwargs)
|
||||
@ -47,7 +61,8 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
|
||||
'album_artist': 'Carlo Ambrosio',
|
||||
'artist': 'Carlo Ambrosio & Fabio Di Bari, Carlo Ambrosio',
|
||||
'release_year': '2009',
|
||||
}
|
||||
},
|
||||
'skip': 'Travis CI servers blocked by YandexMusic',
|
||||
}
|
||||
|
||||
def _get_track_url(self, storage_dir, track_id):
|
||||
@ -139,6 +154,7 @@ class YandexMusicAlbumIE(YandexMusicPlaylistBaseIE):
|
||||
'title': 'Carlo Ambrosio - Gypsy Soul (2009)',
|
||||
},
|
||||
'playlist_count': 50,
|
||||
'skip': 'Travis CI servers blocked by YandexMusic',
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
@ -171,6 +187,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
|
||||
'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9',
|
||||
},
|
||||
'playlist_count': 6,
|
||||
'skip': 'Travis CI servers blocked by YandexMusic',
|
||||
}, {
|
||||
# playlist exceeding the limit of 150 tracks shipped with webpage (see
|
||||
# https://github.com/rg3/youtube-dl/issues/6666)
|
||||
@ -180,6 +197,7 @@ class YandexMusicPlaylistIE(YandexMusicPlaylistBaseIE):
|
||||
'title': 'Музыка 90-х',
|
||||
},
|
||||
'playlist_count': 310,
|
||||
'skip': 'Travis CI servers blocked by YandexMusic',
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
||||
@ -2139,10 +2139,11 @@ class YoutubeSearchDateIE(YoutubeSearchIE):
|
||||
_EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
|
||||
|
||||
|
||||
class YoutubeSearchURLIE(InfoExtractor):
|
||||
class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
|
||||
IE_DESC = 'YouTube.com search URLs'
|
||||
IE_NAME = 'youtube:search_url'
|
||||
_VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
|
||||
_VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
|
||||
'playlist_mincount': 5,
|
||||
@ -2157,32 +2158,8 @@ class YoutubeSearchURLIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
mobj = re.match(self._VALID_URL, url)
|
||||
query = compat_urllib_parse_unquote_plus(mobj.group('query'))
|
||||
|
||||
webpage = self._download_webpage(url, query)
|
||||
result_code = self._search_regex(
|
||||
r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML')
|
||||
|
||||
part_codes = re.findall(
|
||||
r'(?s)<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*>(.*?)</h3>', result_code)
|
||||
entries = []
|
||||
for part_code in part_codes:
|
||||
part_title = self._html_search_regex(
|
||||
[r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False)
|
||||
part_url_snippet = self._html_search_regex(
|
||||
r'(?s)href="([^"]+)"', part_code, 'item URL')
|
||||
part_url = compat_urlparse.urljoin(
|
||||
'https://www.youtube.com/', part_url_snippet)
|
||||
entries.append({
|
||||
'_type': 'url',
|
||||
'url': part_url,
|
||||
'title': part_title,
|
||||
})
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'entries': entries,
|
||||
'title': query,
|
||||
}
|
||||
return self.playlist_result(self._process_page(webpage), playlist_title=query)
|
||||
|
||||
|
||||
class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user