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

Merge branch 'master' into Vimeo-issue-16717

Browse Source
This commit is contained in:
Parmjit Virk 2018-07-18 20:46:10 -05:00
commit 8c940e6ceb
8 changed files with 218 additions and 162 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
youtube_dl/extractor/common.py
View File

@ -1859,9 +1859,7 @@ class InfoExtractor(object):
'height': height, 'height': height,
}) })
formats.extend(m3u8_formats) formats.extend(m3u8_formats)
continue elif src_ext == 'f4m':
if src_ext == 'f4m':
f4m_url = src_url f4m_url = src_url
if not f4m_params: if not f4m_params:
f4m_params = { f4m_params = {
@ -1871,9 +1869,13 @@ class InfoExtractor(object):
f4m_url += '&' if '?' in f4m_url else '?' f4m_url += '&' if '?' in f4m_url else '?'
f4m_url += compat_urllib_parse_urlencode(f4m_params) f4m_url += compat_urllib_parse_urlencode(f4m_params)
formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False)) formats.extend(self._extract_f4m_formats(f4m_url, video_id, f4m_id='hds', fatal=False))
continue elif src_ext == 'mpd':
formats.extend(self._extract_mpd_formats(
if src_url.startswith('http') and self._is_valid_url(src, video_id): src_url, video_id, mpd_id='dash', fatal=False))
elif re.search(r'\.ism/[Mm]anifest', src_url):
formats.extend(self._extract_ism_formats(
src_url, video_id, ism_id='mss', fatal=False))
elif src_url.startswith('http') and self._is_valid_url(src, video_id):
http_count += 1 http_count += 1
formats.append({ formats.append({
'url': src_url, 'url': src_url,
@ -1884,7 +1886,6 @@ class InfoExtractor(object):
'width': width, 'width': width,
'height': height, 'height': height,
}) })
continue
return formats return formats

3
youtube_dl/extractor/dailymotion.py
View File

@ -144,7 +144,8 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
description = self._og_search_description(webpage) or self._html_search_meta( description = self._og_search_description(
webpage, default=None) or self._html_search_meta(
'description', webpage, 'description') 'description', webpage, 'description')
view_count_str = self._search_regex( view_count_str = self._search_regex(

15
youtube_dl/extractor/facebook.py
View File

@ -20,6 +20,7 @@ from ..utils import (
int_or_none, int_or_none,
js_to_json, js_to_json,
limit_length, limit_length,
parse_count,
sanitized_Request, sanitized_Request,
try_get, try_get,
urlencode_postdata, urlencode_postdata,
@ -75,7 +76,7 @@ class FacebookIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '274175099429670', 'id': '274175099429670',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Asif Nawab Butt posted a video to his Timeline.', 'title': 're:^Asif Nawab Butt posted a video',
'uploader': 'Asif Nawab Butt', 'uploader': 'Asif Nawab Butt',
'upload_date': '20140506', 'upload_date': '20140506',
'timestamp': 1399398998, 'timestamp': 1399398998,
@ -133,7 +134,7 @@ class FacebookIE(InfoExtractor):
}, { }, {
# have 1080P, but only up to 720p in swf params # have 1080P, but only up to 720p in swf params
'url': 'https://www.facebook.com/cnn/videos/10155529876156509/', 'url': 'https://www.facebook.com/cnn/videos/10155529876156509/',
'md5': '0d9813160b146b3bc8744e006027fcc6', 'md5': '9571fae53d4165bbbadb17a94651dcdc',
'info_dict': { 'info_dict': {
'id': '10155529876156509', 'id': '10155529876156509',
'ext': 'mp4', 'ext': 'mp4',
@ -142,6 +143,7 @@ class FacebookIE(InfoExtractor):
'upload_date': '20161030', 'upload_date': '20161030',
'uploader': 'CNN', 'uploader': 'CNN',
'thumbnail': r're:^https?://.*', 'thumbnail': r're:^https?://.*',
'view_count': int,
}, },
}, { }, {
# bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall # bigPipe.onPageletArrive ... onPageletArrive pagelet_group_mall
@ -149,7 +151,7 @@ class FacebookIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '1417995061575415', 'id': '1417995061575415',
'ext': 'mp4', 'ext': 'mp4',
'title': 'md5:a7b86ca673f51800cd54687b7f4012fe', 'title': 'md5:1db063d6a8c13faa8da727817339c857',
'timestamp': 1486648217, 'timestamp': 1486648217,
'upload_date': '20170209', 'upload_date': '20170209',
'uploader': 'Yaroslav Korpan', 'uploader': 'Yaroslav Korpan',
@ -176,7 +178,7 @@ class FacebookIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '1396382447100162', 'id': '1396382447100162',
'ext': 'mp4', 'ext': 'mp4',
'title': 'md5:e2d2700afdf84e121f5d0f999bad13a3', 'title': 'md5:19a428bbde91364e3de815383b54a235',
'timestamp': 1486035494, 'timestamp': 1486035494,
'upload_date': '20170202', 'upload_date': '20170202',
'uploader': 'Elisabeth Ahtn', 'uploader': 'Elisabeth Ahtn',
@ -426,6 +428,10 @@ class FacebookIE(InfoExtractor):
'timestamp', default=None)) 'timestamp', default=None))
thumbnail = self._og_search_thumbnail(webpage) thumbnail = self._og_search_thumbnail(webpage)
view_count = parse_count(self._search_regex(
r'\bviewCount\s*:\s*["\']([\d,.]+)', webpage, 'view count',
default=None))
info_dict = { info_dict = {
'id': video_id, 'id': video_id,
'title': video_title, 'title': video_title,
@ -433,6 +439,7 @@ class FacebookIE(InfoExtractor):
'uploader': uploader, 'uploader': uploader,
'timestamp': timestamp, 'timestamp': timestamp,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'view_count': view_count,
} }
return webpage, info_dict return webpage, info_dict

5
youtube_dl/extractor/imgur.py
View File

@ -12,7 +12,7 @@ from ..utils import (
class ImgurIE(InfoExtractor): class ImgurIE(InfoExtractor):
_VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z]+)?$' _VALID_URL = r'https?://(?:i\.)?imgur\.com/(?:(?:gallery|(?:topic|r)/[^/]+)/)?(?P<id>[a-zA-Z0-9]{6,})(?:[/?#&]+|\.[a-z0-9]+)?$'
_TESTS = [{ _TESTS = [{
'url': 'https://i.imgur.com/A61SaA1.gifv', 'url': 'https://i.imgur.com/A61SaA1.gifv',
@ -43,6 +43,9 @@ class ImgurIE(InfoExtractor):
}, { }, {
'url': 'http://imgur.com/r/aww/VQcQPhM', 'url': 'http://imgur.com/r/aww/VQcQPhM',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://i.imgur.com/crGpqCV.mp4',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):

155
youtube_dl/extractor/mediaset.py
View File

@ -3,75 +3,75 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .theplatform import ThePlatformBaseIE
from ..compat import compat_str
from ..utils import ( from ..utils import (
determine_ext, ExtractorError,
parse_duration, int_or_none,
try_get, update_url_query,
unified_strdate,
) )
class MediasetIE(InfoExtractor): class MediasetIE(ThePlatformBaseIE):
_TP_TLD = 'eu'
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
(?: (?:
mediaset:| mediaset:|
https?:// https?://
(?:www\.)?video\.mediaset\.it/ (?:(?:www|static3)\.)?mediasetplay\.mediaset\.it/
(?: (?:
(?:video|on-demand)/(?:[^/]+/)+[^/]+_| (?:video|on-demand)/(?:[^/]+/)+[^/]+_|
player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid= player/index\.html\?.*?\bprogramGuid=
) )
)(?P<id>[0-9]+) )(?P<id>[0-9A-Z]{16})
''' '''
_TESTS = [{ _TESTS = [{
# full episode # full episode
'url': 'http://www.video.mediaset.it/video/hello_goodbye/full/quarta-puntata_661824.html', 'url': 'https://www.mediasetplay.mediaset.it/video/hellogoodbye/quarta-puntata_FAFU000000661824',
'md5': '9b75534d42c44ecef7bf1ffeacb7f85d', 'md5': '9b75534d42c44ecef7bf1ffeacb7f85d',
'info_dict': { 'info_dict': {
'id': '661824', 'id': 'FAFU000000661824',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Quarta puntata', 'title': 'Quarta puntata',
'description': 'md5:7183696d6df570e3412a5ef74b27c5e2', 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 1414, 'duration': 1414.26,
'creator': 'mediaset',
'upload_date': '20161107', 'upload_date': '20161107',
'series': 'Hello Goodbye', 'series': 'Hello Goodbye',
'categories': ['reality'], 'timestamp': 1478532900,
'uploader': 'Rete 4',
'uploader_id': 'R4',
}, },
'expected_warnings': ['is not a supported codec'],
}, { }, {
'url': 'http://www.video.mediaset.it/video/matrix/full_chiambretti/puntata-del-25-maggio_846685.html', 'url': 'https://www.mediasetplay.mediaset.it/video/matrix/puntata-del-25-maggio_F309013801000501',
'md5': '1276f966ac423d16ba255ce867de073e', 'md5': '288532f0ad18307705b01e581304cd7b',
'info_dict': { 'info_dict': {
'id': '846685', 'id': 'F309013801000501',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Puntata del 25 maggio', 'title': 'Puntata del 25 maggio',
'description': 'md5:ee2e456e3eb1dba5e814596655bb5296', 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 6565, 'duration': 6565.007,
'creator': 'mediaset', 'upload_date': '20180526',
'upload_date': '20180525',
'series': 'Matrix', 'series': 'Matrix',
'categories': ['infotainment'], 'timestamp': 1527326245,
'uploader': 'Canale 5',
'uploader_id': 'C5',
}, },
'expected_warnings': ['HTTP Error 403: Forbidden'], 'expected_warnings': ['HTTP Error 403: Forbidden'],
}, { }, {
# clip # clip
'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html', 'url': 'https://www.mediasetplay.mediaset.it/video/gogglebox/un-grande-classico-della-commedia-sexy_FAFU000000661680',
'only_matching': True, 'only_matching': True,
}, { }, {
# iframe simple # iframe simple
'url': 'http://www.video.mediaset.it/player/playerIFrame.shtml?id=665924&autoplay=true', 'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665924&id=665924',
'only_matching': True, 'only_matching': True,
}, { }, {
# iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/) # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
'url': 'https://www.video.mediaset.it/player/playerIFrameTwitter.shtml?id=665104&playrelated=false&autoplay=false&related=true&hidesocial=true', 'url': 'https://static3.mediasetplay.mediaset.it/player/index.html?appKey=5ad3966b1de1c4000d5cec48&programGuid=FAFU000000665104&id=665104',
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'mediaset:661824', 'url': 'mediaset:FAFU000000665924',
'only_matching': True, 'only_matching': True,
}] }]
@ -84,61 +84,54 @@ class MediasetIE(InfoExtractor):
webpage)] webpage)]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) guid = self._match_id(url)
tp_path = 'PR1GhC/media/guid/2702976343/' + guid
video = self._download_json( info = self._extract_theplatform_metadata(tp_path, guid)
'https://www.video.mediaset.it/html/metainfo.sjson',
video_id, 'Downloading media info', query={
'id': video_id
})['video']
title = video['title']
media_id = video.get('guid') or video_id
video_list = self._download_json(
'http://cdnsel01.mediaset.net/GetCdn2018.aspx',
video_id, 'Downloading video CDN JSON', query={
'streamid': media_id,
'format': 'json',
})['videoList']
formats = [] formats = []
for format_url in video_list: subtitles = {}
ext = determine_ext(format_url) first_e = None
if ext == 'm3u8': for asset_type in ('SD', 'HD'):
formats.extend(self._extract_m3u8_formats( for f in ('MPEG4', 'MPEG-DASH', 'M3U', 'ISM'):
format_url, video_id, 'mp4', entry_protocol='m3u8_native', try:
m3u8_id='hls', fatal=False)) tp_formats, tp_subtitles = self._extract_theplatform_smil(
elif ext == 'mpd': update_url_query('http://link.theplatform.%s/s/%s' % (self._TP_TLD, tp_path), {
formats.extend(self._extract_mpd_formats( 'mbr': 'true',
format_url, video_id, mpd_id='dash', fatal=False)) 'formats': f,
elif ext == 'ism' or '.ism' in format_url: 'assetTypes': asset_type,
formats.extend(self._extract_ism_formats( }), guid, 'Downloading %s %s SMIL data' % (f, asset_type))
format_url, video_id, ism_id='mss', fatal=False)) except ExtractorError as e:
else: if not first_e:
formats.append({ first_e = e
'url': format_url, break
'format_id': determine_ext(format_url), for tp_f in tp_formats:
}) tp_f['quality'] = 1 if asset_type == 'HD' else 0
formats.extend(tp_formats)
subtitles = self._merge_subtitles(subtitles, tp_subtitles)
if first_e and not formats:
raise first_e
self._sort_formats(formats) self._sort_formats(formats)
creator = try_get( fields = []
video, lambda x: x['brand-info']['publisher'], compat_str) for templ, repls in (('tvSeason%sNumber', ('', 'Episode')), ('mediasetprogram$%s', ('brandTitle', 'numberOfViews', 'publishInfo'))):
category = try_get( fields.extend(templ % repl for repl in repls)
video, lambda x: x['brand-info']['category'], compat_str) feed_data = self._download_json(
categories = [category] if category else None 'https://feed.entertainment.tv.theplatform.eu/f/PR1GhC/mediaset-prod-all-programs/guid/-/' + guid,
guid, fatal=False, query={'fields': ','.join(fields)})
if feed_data:
publish_info = feed_data.get('mediasetprogram$publishInfo') or {}
info.update({
'episode_number': int_or_none(feed_data.get('tvSeasonEpisodeNumber')),
'season_number': int_or_none(feed_data.get('tvSeasonNumber')),
'series': feed_data.get('mediasetprogram$brandTitle'),
'uploader': publish_info.get('description'),
'uploader_id': publish_info.get('channel'),
'view_count': int_or_none(feed_data.get('mediasetprogram$numberOfViews')),
})
return { info.update({
'id': video_id, 'id': guid,
'title': title,
'description': video.get('short-description'),
'thumbnail': video.get('thumbnail'),
'duration': parse_duration(video.get('duration')),
'creator': creator,
'upload_date': unified_strdate(video.get('production-date')),
'webpage_url': video.get('url'),
'series': video.get('brand-value'),
'season': video.get('season'),
'categories': categories,
'formats': formats, 'formats': formats,
} 'subtitles': subtitles,
})
return info

125
youtube_dl/extractor/pornhub.py
View File

@ -4,28 +4,21 @@ from __future__ import unicode_literals
import functools import functools
import itertools import itertools
import operator import operator
# import os
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_HTTPError, compat_HTTPError,
# compat_urllib_parse_unquote, compat_str,
# compat_urllib_parse_unquote_plus,
# compat_urllib_parse_urlparse,
) )
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
int_or_none, int_or_none,
js_to_json, js_to_json,
orderedSet, orderedSet,
# sanitized_Request,
remove_quotes, remove_quotes,
str_to_int, str_to_int,
) )
# from ..aes import (
# aes_decrypt_text
# )
class PornHubIE(InfoExtractor): class PornHubIE(InfoExtractor):
@ -62,7 +55,7 @@ class PornHubIE(InfoExtractor):
'id': '1331683002', 'id': '1331683002',
'ext': 'mp4', 'ext': 'mp4',
'title': '重庆婷婷女王足交', 'title': '重庆婷婷女王足交',
'uploader': 'cj397186295', 'uploader': 'Unknown',
'duration': 1753, 'duration': 1753,
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
@ -121,7 +114,7 @@ class PornHubIE(InfoExtractor):
self._set_cookie('pornhub.com', 'platform', platform) self._set_cookie('pornhub.com', 'platform', platform)
return self._download_webpage( return self._download_webpage(
'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id, 'http://www.pornhub.com/view_video.php?viewkey=%s' % video_id,
video_id) video_id, 'Downloading %s webpage' % platform)
webpage = dl_webpage('pc') webpage = dl_webpage('pc')
@ -134,48 +127,19 @@ class PornHubIE(InfoExtractor):
'PornHub said: %s' % error_msg, 'PornHub said: %s' % error_msg,
expected=True, video_id=video_id) expected=True, video_id=video_id)
tv_webpage = dl_webpage('tv')
assignments = self._search_regex(
r'(var.+?mediastring.+?)</script>', tv_webpage,
'encoded url').split(';')
js_vars = {}
def parse_js_value(inp):
inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
if '+' in inp:
inps = inp.split('+')
return functools.reduce(
operator.concat, map(parse_js_value, inps))
inp = inp.strip()
if inp in js_vars:
return js_vars[inp]
return remove_quotes(inp)
for assn in assignments:
assn = assn.strip()
if not assn:
continue
assn = re.sub(r'var\s+', '', assn)
vname, value = assn.split('=', 1)
js_vars[vname] = parse_js_value(value)
video_url = js_vars['mediastring']
title = self._search_regex(
r'<h1>([^>]+)</h1>', tv_webpage, 'title', default=None)
# video_title from flashvars contains whitespace instead of non-ASCII (see # video_title from flashvars contains whitespace instead of non-ASCII (see
# http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
# on that anymore. # on that anymore.
title = title or self._html_search_meta( title = self._html_search_meta(
'twitter:title', webpage, default=None) or self._search_regex( 'twitter:title', webpage, default=None) or self._search_regex(
(r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)', (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1', r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'), r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
webpage, 'title', group='title') webpage, 'title', group='title')
video_urls = []
video_urls_set = set()
flashvars = self._parse_json( flashvars = self._parse_json(
self._search_regex( self._search_regex(
r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'), r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
@ -183,8 +147,78 @@ class PornHubIE(InfoExtractor):
if flashvars: if flashvars:
thumbnail = flashvars.get('image_url') thumbnail = flashvars.get('image_url')
duration = int_or_none(flashvars.get('video_duration')) duration = int_or_none(flashvars.get('video_duration'))
media_definitions = flashvars.get('mediaDefinitions')
if isinstance(media_definitions, list):
for definition in media_definitions:
if not isinstance(definition, dict):
continue
video_url = definition.get('videoUrl')
if not video_url or not isinstance(video_url, compat_str):
continue
if video_url in video_urls_set:
continue
video_urls_set.add(video_url)
video_urls.append(
(video_url, int_or_none(definition.get('quality'))))
else: else:
title, thumbnail, duration = [None] * 3 thumbnail, duration = [None] * 2
if not video_urls:
tv_webpage = dl_webpage('tv')
assignments = self._search_regex(
r'(var.+?mediastring.+?)</script>', tv_webpage,
'encoded url').split(';')
js_vars = {}
def parse_js_value(inp):
inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
if '+' in inp:
inps = inp.split('+')
return functools.reduce(
operator.concat, map(parse_js_value, inps))
inp = inp.strip()
if inp in js_vars:
return js_vars[inp]
return remove_quotes(inp)
for assn in assignments:
assn = assn.strip()
if not assn:
continue
assn = re.sub(r'var\s+', '', assn)
vname, value = assn.split('=', 1)
js_vars[vname] = parse_js_value(value)
video_url = js_vars['mediastring']
if video_url not in video_urls_set:
video_urls.append((video_url, None))
video_urls_set.add(video_url)
for mobj in re.finditer(
r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage):
video_url = mobj.group('url')
if video_url not in video_urls_set:
video_urls.append((video_url, None))
video_urls_set.add(video_url)
formats = []
for video_url, height in video_urls:
tbr = None
mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
if mobj:
if not height:
height = int(mobj.group('height'))
tbr = int(mobj.group('tbr'))
formats.append({
'url': video_url,
'format_id': '%dp' % height if height else None,
'height': height,
'tbr': tbr,
})
self._sort_formats(formats)
video_uploader = self._html_search_regex( video_uploader = self._html_search_regex(
r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<', r'(?s)From:&nbsp;.+?<(?:a\b[^>]+\bhref=["\']/(?:user|channel)s/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
@ -210,7 +244,6 @@ class PornHubIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'url': video_url,
'uploader': video_uploader, 'uploader': video_uploader,
'title': title, 'title': title,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
@ -219,7 +252,7 @@ class PornHubIE(InfoExtractor):
'like_count': like_count, 'like_count': like_count,
'dislike_count': dislike_count, 'dislike_count': dislike_count,
'comment_count': comment_count, 'comment_count': comment_count,
# 'formats': formats, 'formats': formats,
'age_limit': 18, 'age_limit': 18,
'tags': tags, 'tags': tags,
'categories': categories, 'categories': categories,

57
youtube_dl/extractor/slutload.py
View File

@ -1,12 +1,10 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
from .common import InfoExtractor from .common import InfoExtractor
class SlutloadIE(InfoExtractor): class SlutloadIE(InfoExtractor):
_VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$' _VALID_URL = r'https?://(?:\w+\.)?slutload\.com/(?:video/[^/]+|embed_player|watch)/(?P<id>[^/]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/', 'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
'md5': '868309628ba00fd488cf516a113fd717', 'md5': '868309628ba00fd488cf516a113fd717',
@ -16,33 +14,52 @@ class SlutloadIE(InfoExtractor):
'title': 'virginie baisee en cam', 'title': 'virginie baisee en cam',
'age_limit': 18, 'age_limit': 18,
'thumbnail': r're:https?://.*?\.jpg' 'thumbnail': r're:https?://.*?\.jpg'
} },
}, { }, {
# mobile site # mobile site
'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/', 'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://www.slutload.com/embed_player/TD73btpBqSxc/',
'only_matching': True,
}, {
'url': 'http://www.slutload.com/watch/TD73btpBqSxc/Virginie-Baisee-En-Cam.html',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
desktop_url = re.sub(r'^(https?://)mobile\.', r'\1', url) embed_page = self._download_webpage(
webpage = self._download_webpage(desktop_url, video_id) 'http://www.slutload.com/embed_player/%s' % video_id, video_id,
'Downloading embed page', fatal=False)
video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>', if embed_page:
webpage, 'title').strip() def extract(what):
return self._html_search_regex(
r'data-video-%s=(["\'])(?P<url>(?:(?!\1).)+)\1' % what,
embed_page, 'video %s' % what, default=None, group='url')
video_url = self._html_search_regex( video_url = extract('url')
r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"', if video_url:
webpage, 'video URL') title = self._html_search_regex(
thumbnail = self._html_search_regex( r'<title>([^<]+)', embed_page, 'title', default=video_id)
r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"', return {
webpage, 'thumbnail', fatal=False) 'id': video_id,
'url': video_url,
'title': title,
'thumbnail': extract('preview'),
'age_limit': 18
}
return { webpage = self._download_webpage(
'http://www.slutload.com/video/_/%s/' % video_id, video_id)
title = self._html_search_regex(
r'<h1><strong>([^<]+)</strong>', webpage, 'title').strip()
info = self._parse_html5_media_entries(url, webpage, video_id)[0]
info.update({
'id': video_id, 'id': video_id,
'url': video_url, 'title': title,
'title': video_title, 'age_limit': 18,
'thumbnail': thumbnail, })
'age_limit': 18 return info
}

5
youtube_dl/extractor/theplatform.py
View File

@ -32,13 +32,14 @@ _x = lambda p: xpath_with_ns(p, {'smil': default_ns})
class ThePlatformBaseIE(OnceIE): class ThePlatformBaseIE(OnceIE):
_TP_TLD = 'com'
def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'): def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
meta = self._download_xml( meta = self._download_xml(
smil_url, video_id, note=note, query={'format': 'SMIL'}, smil_url, video_id, note=note, query={'format': 'SMIL'},
headers=self.geo_verification_headers()) headers=self.geo_verification_headers())
error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src') error_element = find_xpath_attr(meta, _x('.//smil:ref'), 'src')
if error_element is not None and error_element.attrib['src'].startswith( if error_element is not None and error_element.attrib['src'].startswith(
'http://link.theplatform.com/s/errorFiles/Unavailable.'): 'http://link.theplatform.%s/s/errorFiles/Unavailable.' % self._TP_TLD):
raise ExtractorError(error_element.attrib['abstract'], expected=True) raise ExtractorError(error_element.attrib['abstract'], expected=True)
smil_formats = self._parse_smil_formats( smil_formats = self._parse_smil_formats(
@ -66,7 +67,7 @@ class ThePlatformBaseIE(OnceIE):
return formats, subtitles return formats, subtitles
def _download_theplatform_metadata(self, path, video_id): def _download_theplatform_metadata(self, path, video_id):
info_url = 'http://link.theplatform.com/s/%s?format=preview' % path info_url = 'http://link.theplatform.%s/s/%s?format=preview' % (self._TP_TLD, path)
return self._download_json(info_url, video_id) return self._download_json(info_url, video_id)
def _parse_theplatform_metadata(self, info): def _parse_theplatform_metadata(self, info):