2 from __future__
import unicode_literals
10 from .common
import InfoExtractor
11 from ..compat
import (
14 compat_urllib_request
,
16 from .openload
import PhantomJSwrapper
33 class PornHubBaseIE(InfoExtractor
):
34 _NETRC_MACHINE
= 'pornhub'
35 _PORNHUB_HOST_RE
= r
'(?:(?P<host>pornhub(?:premium)?\.(?:com|net|org))|pornhubthbh7ap3u\.onion)'
37 def _download_webpage_handle(self
, *args
, **kwargs
):
38 def dl(*args
, **kwargs
):
39 return super(PornHubBaseIE
, self
)._download
_webpage
_handle
(*args
, **kwargs
)
41 ret
= dl(*args
, **kwargs
)
48 if any(re
.search(p
, webpage
) for p
in (
49 r
'<body\b[^>]+\bonload=["\']go\
(\
)',
50 r'document\
.cookie\s
*=\s
*["\']RNKEY=',
51 r'document\.location\.reload\(true\)')):
52 url_or_request = args[0]
53 url = (url_or_request.get_full_url()
54 if isinstance(url_or_request, compat_urllib_request.Request)
56 phantom = PhantomJSwrapper(self, required_version='2.0')
57 phantom.get(url, html=webpage)
58 webpage, urlh = dl(*args, **kwargs)
62 def _real_initialize(self):
63 self._logged_in = False
65 def _login(self, host):
69 site = host.split('.')[0]
71 # Both sites pornhub and pornhubpremium have separate accounts
72 # so there should be an option to provide credentials for both.
73 # At the same time some videos are available under the same video id
74 # on both sites so that we have to identify them as the same video.
75 # For that purpose we have to keep both in the same extractor
76 # but under different netrc machines.
77 username, password = self._get_login_info(netrc_machine=site)
81 login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '')
82 login_page = self._download_webpage(
83 login_url, None, 'Downloading %s login page' % site)
85 def is_logged(webpage):
86 return any(re.search(p, webpage) for p in (
87 r'class=["\']signOut
',
88 r'>Sign\s
+[Oo
]ut\s
*<'))
90 if is_logged(login_page):
91 self._logged_in = True
94 login_form = self._hidden_inputs(login_page)
101 response = self._download_json(
102 'https
://www
.%s/front
/authenticate
' % host, None,
103 'Logging
in to
%s' % site,
104 data=urlencode_postdata(login_form),
106 'Content
-Type
': 'application
/x
-www
-form
-urlencoded
; charset
=UTF
-8',
107 'Referer
': login_url,
108 'X
-Requested
-With
': 'XMLHttpRequest
',
111 if response.get('success
') == '1':
112 self._logged_in = True
115 message = response.get('message
')
116 if message is not None:
117 raise ExtractorError(
118 'Unable to login
: %s' % message, expected=True)
120 raise ExtractorError('Unable to log
in')
123 class PornHubIE(PornHubBaseIE):
124 IE_DESC = 'PornHub
and Thumbzilla
'
125 _VALID_URL = r'''(?x)
130 /(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
131 (?:www\.)?thumbzilla\.com/video/
134 ''' % PornHubBaseIE._PORNHUB_HOST_RE
136 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=648719015',
137 'md5
': 'a6391306d050e4547f62b3f485dd9ba9
',
141 'title
': 'Seductive Indian beauty strips down
and fingers her pink pussy
',
143 'upload_date
': '20130628',
144 'timestamp
': 1372447216,
148 'dislike_count
': int,
149 'comment_count
': int,
157 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=1331683002',
162 'upload_date
': '20150213',
163 'timestamp
': 1423804862,
167 'dislike_count
': int,
168 'comment_count
': int,
174 'skip_download
': True,
176 'skip
': 'Video has been flagged
for verification
in accordance
with our trust
and safety policy
',
179 'url
': 'https
://www
.pornhub
.com
/view_video
.php?viewkey
=ph5af5fef7c2aa7
',
181 'id': 'ph5af5fef7c2aa7
',
183 'title
': 'BFFS
- Cute Teen Girls Share Cock On the Floor
',
188 'dislike_count
': int,
189 'comment_count
': int,
200 'skip_download
': True,
202 'skip
': 'This video has been disabled
',
204 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=ph557bbb6676d2d
',
205 'only_matching
': True,
207 # removed at the request of cam4.com
208 'url
': 'http
://fr
.pornhub
.com
/view_video
.php?viewkey
=ph55ca2f9760862
',
209 'only_matching
': True,
211 # removed at the request of the copyright owner
212 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=788152859',
213 'only_matching
': True,
215 # removed by uploader
216 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=ph572716d15a111
',
217 'only_matching
': True,
220 'url
': 'http
://www
.pornhub
.com
/view_video
.php?viewkey
=ph56fd731fce6b7
',
221 'only_matching
': True,
223 'url
': 'https
://www
.thumbzilla
.com
/video
/ph56c6114abd99a
/horny
-girlfriend
-sex
',
224 'only_matching
': True,
226 'url
': 'http
://www
.pornhub
.com
/video
/show?viewkey
=648719015',
227 'only_matching
': True,
229 'url
': 'https
://www
.pornhub
.net
/view_video
.php?viewkey
=203640933',
230 'only_matching
': True,
232 'url
': 'https
://www
.pornhub
.org
/view_video
.php?viewkey
=203640933',
233 'only_matching
': True,
235 'url
': 'https
://www
.pornhubpremium
.com
/view_video
.php?viewkey
=ph5e4acdae54a82
',
236 'only_matching
': True,
238 # Some videos are available with the same id on both premium
239 # and non-premium sites (e.g. this and the following test)
240 'url
': 'https
://www
.pornhub
.com
/view_video
.php?viewkey
=ph5f75b0f4b18e3
',
241 'only_matching
': True,
243 'url
': 'https
://www
.pornhubpremium
.com
/view_video
.php?viewkey
=ph5f75b0f4b18e3
',
244 'only_matching
': True,
247 'url
': 'https
://www
.pornhub
.com
/view_video
.php?viewkey
=ph5a9813bfa7156
',
248 'only_matching
': True,
250 'url
': 'http
://pornhubthbh7ap3u
.onion
/view_video
.php?viewkey
=ph5a9813bfa7156
',
251 'only_matching
': True,
255 def _extract_urls(webpage):
257 r'<iframe
[^
>]+?src
=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)',
260 def _extract_count(self, pattern, webpage, name):
261 return str_to_int(self._search_regex(
262 pattern, webpage, '%s count' % name, fatal=False))
264 def _real_extract(self, url):
265 mobj = self._match_valid_url(url)
266 host = mobj.group('host') or 'pornhub.com'
267 video_id = mobj.group('id')
271 self._set_cookie(host, 'age_verified', '1')
273 def dl_webpage(platform):
274 self._set_cookie(host, 'platform', platform)
275 return self._download_webpage(
276 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
277 video_id, 'Downloading %s webpage' % platform)
279 webpage = dl_webpage('pc')
281 error_msg = self._html_search_regex(
282 (r'(?s)<div[^>]+class=(["\'])(?
:(?
!\
1).)*\b(?
:removed|userMessageSection
)\b(?
:(?
!\
1).)*\
1[^
>]*>(?P
<error
>.+?
)</div
>',
283 r'(?s
)<section
[^
>]+class=["\']noVideo["\'][^
>]*>(?P
<error
>.+?
)</section
>'),
284 webpage, 'error message
', default=None, group='error
')
286 error_msg = re.sub(r'\s
+', ' ', error_msg)
287 raise ExtractorError(
288 'PornHub said
: %s' % error_msg,
289 expected=True, video_id=video_id)
291 if any(re.search(p, webpage) for p in (
292 r'class=["\']geoBlocked["\']',
293 r'>\s
*This content
is unavailable
in your country
')):
294 self.raise_geo_restricted()
296 # video_title from flashvars contains whitespace instead of non-ASCII (see
297 # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
299 title = self._html_search_meta(
300 'twitter
:title
', webpage, default=None) or self._html_search_regex(
301 (r'(?s
)<h1
[^
>]+class=["\']title["\'][^
>]*>(?P
<title
>.+?
)</h1
>',
302 r'<div
[^
>]+data
-video
-title
=(["\'])(?P<title>(?:(?!\1).)+)\1',
303 r'shareTitle["\']\s
*[=:]\s
*(["\'])(?P<title>(?:(?!\1).)+)\1'),
304 webpage, 'title', group='title')
307 video_urls_set = set()
310 flashvars = self._parse_json(
312 r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
315 subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
317 subtitles.setdefault('en', []).append({
321 thumbnail = flashvars.get('image_url')
322 duration = int_or_none(flashvars.get('video_duration'))
323 media_definitions = flashvars.get('mediaDefinitions')
324 if isinstance(media_definitions, list):
325 for definition in media_definitions:
326 if not isinstance(definition, dict):
328 video_url = definition.get('videoUrl')
329 if not video_url or not isinstance(video_url, compat_str):
331 if video_url in video_urls_set:
333 video_urls_set.add(video_url)
335 (video_url, int_or_none(definition.get('quality'))))
337 thumbnail, duration = [None] * 2
339 def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
340 assignments = self._search_regex(
341 pattern, webpage, 'encoded url', default=default)
345 assignments = assignments.split(';')
349 def parse_js_value(inp):
350 inp = re.sub(r'/\*(?:(?!\*/).)*?\*/', '', inp)
352 inps = inp.split('+')
353 return functools.reduce(
354 operator.concat, map(parse_js_value, inps))
358 return remove_quotes(inp)
360 for assn in assignments:
364 assn = re.sub(r'var\s+', '', assn)
365 vname, value = assn.split('=', 1)
366 js_vars[vname] = parse_js_value(value)
369 def add_video_url(video_url):
370 v_url = url_or_none(video_url)
373 if v_url in video_urls_set:
375 video_urls.append((v_url, None))
376 video_urls_set.add(v_url)
378 def parse_quality_items(quality_items):
379 q_items = self._parse_json(quality_items, video_id, fatal=False)
380 if not isinstance(q_items, list):
383 if isinstance(item, dict):
384 add_video_url(item.get('url'))
387 FORMAT_PREFIXES = ('media', 'quality', 'qualityItems')
388 js_vars = extract_js_vars(
389 webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
392 for key, format_url in js_vars.items():
393 if key.startswith(FORMAT_PREFIXES[-1]):
394 parse_quality_items(format_url)
395 elif any(key.startswith(p) for p in FORMAT_PREFIXES[:2]):
396 add_video_url(format_url)
397 if not video_urls and re.search(
398 r'<[^>]+\bid=["\']lockedPlayer
', webpage):
399 raise ExtractorError(
400 'Video
%s is locked
' % video_id, expected=True)
403 js_vars = extract_js_vars(
404 dl_webpage('tv
'), r'(var
.+?mediastring
.+?
)</script
>')
405 add_video_url(js_vars['mediastring
'])
407 for mobj in re.finditer(
408 r'<a
[^
>]+\bclass
=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P
<url
>(?
:(?
!\
1).)+)\
1',
410 video_url = mobj.group('url
')
411 if video_url not in video_urls_set:
412 video_urls.append((video_url, None))
413 video_urls_set.add(video_url)
418 def add_format(format_url, height=None):
419 ext = determine_ext(format_url)
421 formats.extend(self._extract_mpd_formats(
422 format_url, video_id, mpd_id='dash
', fatal=False))
425 formats.extend(self._extract_m3u8_formats(
426 format_url, video_id, 'mp4
', entry_protocol='m3u8_native
',
427 m3u8_id='hls
', fatal=False))
430 height = int_or_none(self._search_regex(
431 r'(?P
<height
>\d
+)[pP
]?_\d
+[kK
]', format_url, 'height
',
435 'format_id
': '%dp
' % height if height else None,
439 for video_url, height in video_urls:
441 upload_date = self._search_regex(
442 r'/(\d{6}
/\d{2}
)/', video_url, 'upload data
', default=None)
444 upload_date = upload_date.replace('/', '')
445 if '/video
/get_media
' in video_url:
446 medias = self._download_json(video_url, video_id, fatal=False)
447 if isinstance(medias, list):
449 if not isinstance(media, dict):
451 video_url = url_or_none(media.get('videoUrl
'))
454 height = int_or_none(media.get('quality
'))
455 add_format(video_url, height)
457 add_format(video_url)
459 # field_preference is unnecessary here, but kept for code-similarity with youtube-dl
461 formats, field_preference=('height
', 'width
', 'fps
', 'format_id
'))
463 video_uploader = self._html_search_regex(
464 r'(?s
)From
: 
;.+?
<(?
:a
\b[^
>]+\bhref
=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username
)[^
>]+>(.+?
)<',
465 webpage, 'uploader
', default=None)
467 def extract_vote_count(kind, name):
468 return self._extract_count(
469 (r'<span
[^
>]+\bclass
="votes%s"[^
>]*>([\d
,\
.]+)</span
>' % kind,
470 r'<span
[^
>]+\bclass
=["\']votes%s["\'][^
>]*\bdata
-rating
=["\'](\d+)' % kind),
473 view_count = self._extract_count(
474 r'<span class="count
">([\d,\.]+)</span> [Vv]iews', webpage, 'view')
475 like_count = extract_vote_count('Up', 'like')
476 dislike_count = extract_vote_count('Down', 'dislike')
477 comment_count = self._extract_count(
478 r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
480 def extract_list(meta_key):
481 div = self._search_regex(
482 r'(?s)<div[^>]+\bclass=["\'].*?
\b%sWrapper
[^
>]*>(.+?
)</div
>'
483 % meta_key, webpage, meta_key, default=None)
485 return [clean_html(x).strip() for x in re.findall(r'(?s
)<a
[^
>]+\bhref
=[^
>]+>.+?
</a
>', div)]
487 info = self._search_json_ld(webpage, video_id, default={})
488 # description provided in JSON-LD is irrelevant
489 info['description
'] = None
493 'uploader
': video_uploader,
494 'upload_date
': upload_date,
496 'thumbnail
': thumbnail,
497 'duration
': duration,
498 'view_count
': view_count,
499 'like_count
': like_count,
500 'dislike_count
': dislike_count,
501 'comment_count
': comment_count,
504 'tags
': extract_list('tags
'),
505 'categories
': extract_list('categories
'),
506 'cast
': extract_list('pornstars
'),
507 'subtitles
': subtitles,
511 class PornHubPlaylistBaseIE(PornHubBaseIE):
512 def _extract_page(self, url):
513 return int_or_none(self._search_regex(
514 r'\bpage
=(\d
+)', url, 'page
', default=None))
516 def _extract_entries(self, webpage, host):
517 # Only process container div with main playlist content skipping
518 # drop-down menu that uses similar pattern for videos (see
519 # https://github.com/ytdl-org/youtube-dl/issues/11594).
520 container = self._search_regex(
521 r'(?s
)(<div
[^
>]+class=["\']container.+)', webpage,
522 'container', default=webpage)
526 'http://www.%s/%s' % (host, video_url),
527 PornHubIE.ie_key(), video_title=title)
528 for video_url, title in orderedSet(re.findall(
529 r'href="/?
(view_video\
.php
\?.*\bviewkey
=[\da
-z
]+[^
"]*)"[^
>]*\s
+title
="([^"]+)"',
534 class PornHubUserIE(PornHubPlaylistBaseIE):
535 _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)' % PornHubBaseIE._PORNHUB_HOST_RE
537 'url': 'https://www.pornhub.com/model/zoe_ph',
538 'playlist_mincount': 118,
540 'url': 'https://www.pornhub.com/pornstar/liz-vicious',
544 'playlist_mincount': 118,
546 'url': 'https://www.pornhub.com/users/russianveet69',
547 'only_matching': True,
549 'url': 'https://www.pornhub.com/channels/povd',
550 'only_matching': True,
552 'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
553 'only_matching': True,
555 # Unavailable via /videos page, but available with direct pagination
556 # on pornstar page (see [1]), requires premium
557 # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
558 'url': 'https://www.pornhubpremium.com/pornstar/sienna-west',
559 'only_matching': True,
561 # Same as before, multi page
562 'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau',
563 'only_matching': True,
565 'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph',
566 'only_matching': True,
569 def _real_extract(self, url):
570 mobj = self._match_valid_url(url)
571 user_id = mobj.group('id')
572 videos_url = '%s/videos' % mobj.group('url')
573 page = self._extract_page(url)
575 videos_url = update_url_query(videos_url, {'page': page})
576 return self.url_result(
577 videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id)
580 class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
582 def _has_more(webpage):
585 <li[^>]+\bclass=["\']page_next|
586 <link
[^
>]+\brel
=["\']next|
587 <button[^>]+\bid=["\']moreDataBtn
588 ''', webpage) is not None
590 def _entries(self, url, host, item_id):
591 page = self._extract_page(url)
595 def download_page(base_url, num, fallback=False):
596 note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '')
597 return self._download_webpage(
598 base_url, item_id, note, query={'page': num})
601 return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404
604 has_page = page is not None
605 first_page = page if has_page else 1
606 for page_num in (first_page, ) if has_page else itertools.count(first_page):
609 webpage = download_page(base_url, page_num)
610 except ExtractorError as e:
611 # Some sources may not be available via /videos page,
612 # trying to fallback to main page pagination (see [1])
613 # 1. https://github.com/ytdl-org/youtube-dl/issues/27853
614 if is_404(e) and page_num == first_page and VIDEOS in base_url:
615 base_url = base_url.replace(VIDEOS, '')
616 webpage = download_page(base_url, page_num, fallback=True)
619 except ExtractorError as e:
620 if is_404(e) and page_num != first_page:
623 page_entries = self._extract_entries(webpage, host)
626 for e in page_entries:
628 if not self._has_more(webpage):
631 def _real_extract(self, url):
632 mobj = self._match_valid_url(url)
633 host = mobj.group('host')
634 item_id = mobj.group('id')
638 return self.playlist_result(self._entries(url, host, item_id), item_id)
641 class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
642 _VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
644 'url': 'https://www.pornhub.com/model/zoe_ph/videos',
645 'only_matching': True,
647 'url': 'http://www.pornhub.com/users/rushandlia/videos',
648 'only_matching': True,
650 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
652 'id': 'pornstar/jenny-blighe/videos',
654 'playlist_mincount': 149,
656 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
658 'id': 'pornstar/jenny-blighe/videos',
660 'playlist_mincount': 40,
662 # default sorting as Top Rated Videos
663 'url': 'https://www.pornhub.com/channels/povd/videos',
665 'id': 'channels/povd/videos',
667 'playlist_mincount': 293,
670 'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
671 'only_matching': True,
674 'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
675 'only_matching': True,
678 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
679 'only_matching': True,
681 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
682 'only_matching': True,
685 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
686 'only_matching': True,
689 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
690 'only_matching': True,
693 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
694 'only_matching': True,
697 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
698 'only_matching': True,
700 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
701 'only_matching': True,
703 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
704 'only_matching': True,
706 'url': 'https://www.pornhub.com/video',
707 'only_matching': True,
709 'url': 'https://www.pornhub.com/video?page=3',
710 'only_matching': True,
712 'url': 'https://www.pornhub.com/video/search?search=123',
713 'only_matching': True,
715 'url': 'https://www.pornhub.com/categories/teen',
716 'only_matching': True,
718 'url': 'https://www.pornhub.com/categories/teen?page=3',
719 'only_matching': True,
721 'url': 'https://www.pornhub.com/hd',
722 'only_matching': True,
724 'url': 'https://www.pornhub.com/hd?page=3',
725 'only_matching': True,
727 'url': 'https://www.pornhub.com/described-video',
728 'only_matching': True,
730 'url': 'https://www.pornhub.com/described-video?page=2',
731 'only_matching': True,
733 'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
734 'only_matching': True,
736 'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph/videos',
737 'only_matching': True,
741 def suitable(cls, url):
743 if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
744 else super(PornHubPagedVideoListIE, cls).suitable(url))
747 class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
748 _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' % PornHubBaseIE._PORNHUB_HOST_RE
750 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
752 'id': 'jenny-blighe',
754 'playlist_mincount': 129,
756 'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
757 'only_matching': True,
759 'url': 'http://pornhubthbh7ap3u.onion/pornstar/jenny-blighe/videos/upload',
760 'only_matching': True,
764 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
765 _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE
767 'url': 'https://www.pornhub.com/playlist/44121572',
771 'playlist_count': 77,
773 'url': 'https://www.pornhub.com/playlist/4667351',
774 'only_matching': True,
776 'url': 'https://de.pornhub.com/playlist/4667351',
777 'only_matching': True,
779 'url': 'https://de.pornhub.com/playlist/4667351?page=2',
780 'only_matching': True,
783 def _entries(self, url, host, item_id):
784 webpage = self._download_webpage(url, item_id, 'Downloading page 1')
785 playlist_id = self._search_regex(r'var\s+playlistId\s*=\s*"([^"]+)"', webpage, 'playlist_id')
786 video_count = int_or_none(
787 self._search_regex(r'var\s+itemsCount\s*=\s*([0-9]+)\s*\|\|', webpage, 'video_count'))
788 token = self._search_regex(r'var\s+token\s*=\s*"([^"]+)"', webpage, 'token')
789 page_count = math.ceil((video_count - 36) / 40.) + 1
790 page_entries = self._extract_entries(webpage, host)
792 def download_page(page_num):
793 note = 'Downloading page {}'.format(page_num)
794 page_url = 'https://www.{}/playlist/viewChunked'.format(host)
795 return self._download_webpage(page_url, item_id, note, query={
801 for page_num in range(1, page_count + 1):
803 webpage = download_page(page_num)
804 page_entries = self._extract_entries(webpage, host)
807 for e in page_entries:
810 def _real_extract(self, url):
811 mobj = self._match_valid_url(url)
812 host = mobj.group('host')
813 item_id = mobj.group('id')
817 return self.playlist_result(self._entries(mobj.group('url'), host, item_id), item_id)