+# coding: utf-8
from __future__ import unicode_literals
-import os
+import functools
+import itertools
+import operator
import re
from .common import InfoExtractor
-from ..utils import (
- compat_urllib_parse_urlparse,
+from ..compat import (
+ compat_HTTPError,
+ compat_str,
compat_urllib_request,
- compat_urllib_parse,
- str_to_int,
)
-from ..aes import (
- aes_decrypt_text
+from .openload import PhantomJSwrapper
+from ..utils import (
+ determine_ext,
+ ExtractorError,
+ int_or_none,
+ orderedSet,
+ remove_quotes,
+ str_to_int,
+ url_or_none,
)
-class PornHubIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>pornhub\.com/view_video\.php\?viewkey=(?P<videoid>[0-9a-f]+))'
- _TEST = {
+class PornHubBaseIE(InfoExtractor):
+ def _download_webpage_handle(self, *args, **kwargs):
+ def dl(*args, **kwargs):
+ return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs)
+
+ webpage, urlh = dl(*args, **kwargs)
+
+ if any(re.search(p, webpage) for p in (
+ r'<body\b[^>]+\bonload=["\']go\(\)',
+ r'document\.cookie\s*=\s*["\']RNKEY=',
+ r'document\.location\.reload\(true\)')):
+ url_or_request = args[0]
+ url = (url_or_request.get_full_url()
+ if isinstance(url_or_request, compat_urllib_request.Request)
+ else url_or_request)
+ phantom = PhantomJSwrapper(self, required_version='2.0')
+ phantom.get(url, html=webpage)
+ webpage, urlh = dl(*args, **kwargs)
+
+ return webpage, urlh
+
+
+class PornHubIE(PornHubBaseIE):
+ IE_DESC = 'PornHub and Thumbzilla'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+ (?:www\.)?thumbzilla\.com/video/
+ )
+ (?P<id>[\da-z]+)
+ '''
+ _TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
- 'file': '648719015.mp4',
- 'md5': '882f488fa1f0026f023f33576004a2ed',
+ 'md5': '1e19b41231a02eba417839222ac9d58e',
'info_dict': {
- "uploader": "BABES-COM",
- "title": "Seductive Indian beauty strips down and fingers her pink pussy",
- "age_limit": 18
- }
- }
+ 'id': '648719015',
+ 'ext': 'mp4',
+ 'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
+ 'uploader': 'Babes',
+ 'upload_date': '20130628',
+ 'duration': 361,
+ 'view_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'comment_count': int,
+ 'age_limit': 18,
+ 'tags': list,
+ 'categories': list,
+ },
+ }, {
+ # non-ASCII title
+ 'url': 'http://www.pornhub.com/view_video.php?viewkey=1331683002',
+ 'info_dict': {
+ 'id': '1331683002',
+ 'ext': 'mp4',
+ 'title': '重庆婷婷女王足交',
+ 'uploader': 'Unknown',
+ 'upload_date': '20150213',
+ 'duration': 1753,
+ 'view_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'comment_count': int,
+ 'age_limit': 18,
+ 'tags': list,
+ 'categories': list,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ # subtitles
+ 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
+ 'info_dict': {
+ 'id': 'ph5af5fef7c2aa7',
+ 'ext': 'mp4',
+ 'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
+ 'uploader': 'BFFs',
+ 'duration': 622,
+ 'view_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'comment_count': int,
+ 'age_limit': 18,
+ 'tags': list,
+ 'categories': list,
+ 'subtitles': {
+ 'en': [{
+ "ext": 'srt'
+ }]
+ },
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }, {
+ 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
+ 'only_matching': True,
+ }, {
+ # removed at the request of cam4.com
+ 'url': 'http://fr.pornhub.com/view_video.php?viewkey=ph55ca2f9760862',
+ 'only_matching': True,
+ }, {
+ # removed at the request of the copyright owner
+ 'url': 'http://www.pornhub.com/view_video.php?viewkey=788152859',
+ 'only_matching': True,
+ }, {
+ # removed by uploader
+ 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph572716d15a111',
+ 'only_matching': True,
+ }, {
+ # private video
+ 'url': 'http://www.pornhub.com/view_video.php?viewkey=ph56fd731fce6b7',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.thumbzilla.com/video/ph56c6114abd99a/horny-girlfriend-sex',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
+ 'only_matching': True,
+ }]
+
+ @staticmethod
+ def _extract_urls(webpage):
+ return re.findall(
+ r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.(?:com|net)/embed/[\da-z]+)',
+ webpage)
def _extract_count(self, pattern, webpage, name):
- count = self._html_search_regex(pattern, webpage, '%s count' % name, fatal=False)
- if count:
- count = str_to_int(count)
- return count
+ return str_to_int(self._search_regex(
+ pattern, webpage, '%s count' % name, fatal=False))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('videoid')
- url = 'http://www.' + mobj.group('url')
+ host = mobj.group('host') or 'pornhub.com'
+ video_id = mobj.group('id')
- req = compat_urllib_request.Request(url)
- req.add_header('Cookie', 'age_verified=1')
- webpage = self._download_webpage(req, video_id)
+ self._set_cookie(host, 'age_verified', '1')
- video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
- video_uploader = self._html_search_regex(
- r'(?s)From: .+?<(?:a href="/users/|<span class="username)[^>]+>(.+?)<',
- webpage, 'uploader', fatal=False)
- thumbnail = self._html_search_regex(r'"image_url":"([^"]+)', webpage, 'thumbnail', fatal=False)
- if thumbnail:
- thumbnail = compat_urllib_parse.unquote(thumbnail)
+ def dl_webpage(platform):
+ self._set_cookie(host, 'platform', platform)
+ return self._download_webpage(
+ 'https://www.%s/view_video.php?viewkey=%s' % (host, video_id),
+ video_id, 'Downloading %s webpage' % platform)
- view_count = self._extract_count(r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
- like_count = self._extract_count(r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
- dislike_count = self._extract_count(r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
- comment_count = self._extract_count(
- r'All comments \(<var class="videoCommentCount">([\d,\.]+)</var>', webpage, 'comment')
+ webpage = dl_webpage('pc')
- video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage)))
- if webpage.find('"encrypted":true') != -1:
- password = compat_urllib_parse.unquote_plus(self._html_search_regex(r'"video_title":"([^"]+)', webpage, 'password'))
- video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
+ error_msg = self._html_search_regex(
+ r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
+ webpage, 'error message', default=None, group='error')
+ if error_msg:
+ error_msg = re.sub(r'\s+', ' ', error_msg)
+ raise ExtractorError(
+ 'PornHub said: %s' % error_msg,
+ expected=True, video_id=video_id)
- formats = []
- for video_url in video_urls:
- path = compat_urllib_parse_urlparse(video_url).path
- extension = os.path.splitext(path)[1][1:]
- format = path.split('/')[5].split('_')[:2]
- format = "-".join(format)
-
- m = re.match(r'^(?P<height>[0-9]+)P-(?P<tbr>[0-9]+)K$', format)
- if m is None:
- height = None
- tbr = None
- else:
- height = int(m.group('height'))
- tbr = int(m.group('tbr'))
+ # video_title from flashvars contains whitespace instead of non-ASCII (see
+ # http://www.pornhub.com/view_video.php?viewkey=1331683002), not relying
+ # on that anymore.
+ title = self._html_search_meta(
+ 'twitter:title', webpage, default=None) or self._search_regex(
+ (r'<h1[^>]+class=["\']title["\'][^>]*>(?P<title>[^<]+)',
+ r'<div[^>]+data-video-title=(["\'])(?P<title>.+?)\1',
+ r'shareTitle\s*=\s*(["\'])(?P<title>.+?)\1'),
+ webpage, 'title', group='title')
+ video_urls = []
+ video_urls_set = set()
+ subtitles = {}
+
+ flashvars = self._parse_json(
+ self._search_regex(
+ r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
+ video_id)
+ if flashvars:
+ subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
+ if subtitle_url:
+ subtitles.setdefault('en', []).append({
+ 'url': subtitle_url,
+ 'ext': 'srt',
+ })
+ thumbnail = flashvars.get('image_url')
+ 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:
+ 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)
+
+ upload_date = None
+ formats = []
+ for video_url, height in video_urls:
+ if not upload_date:
+ upload_date = self._search_regex(
+ r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
+ if upload_date:
+ upload_date = upload_date.replace('/', '')
+ if determine_ext(video_url) == 'mpd':
+ formats.extend(self._extract_mpd_formats(
+ video_url, video_id, mpd_id='dash', fatal=False))
+ continue
+ 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,
- 'ext': extension,
- 'format': format,
- 'format_id': format,
- 'tbr': tbr,
+ 'format_id': '%dp' % height if height else None,
'height': height,
+ 'tbr': tbr,
})
self._sort_formats(formats)
+ video_uploader = self._html_search_regex(
+ r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:(?:user|channel)s|model|pornstar)/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
+ webpage, 'uploader', fatal=False)
+
+ view_count = self._extract_count(
+ r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
+ like_count = self._extract_count(
+ r'<span class="votesUp">([\d,\.]+)</span>', webpage, 'like')
+ dislike_count = self._extract_count(
+ r'<span class="votesDown">([\d,\.]+)</span>', webpage, 'dislike')
+ comment_count = self._extract_count(
+ r'All Comments\s*<span>\(([\d,.]+)\)', webpage, 'comment')
+
+ def extract_list(meta_key):
+ div = self._search_regex(
+ r'(?s)<div[^>]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)</div>'
+ % meta_key, webpage, meta_key, default=None)
+ if div:
+ return re.findall(r'<a[^>]+\bhref=[^>]+>([^<]+)', div)
+
return {
'id': video_id,
'uploader': video_uploader,
- 'title': video_title,
+ 'upload_date': upload_date,
+ 'title': title,
'thumbnail': thumbnail,
+ 'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
'comment_count': comment_count,
'formats': formats,
'age_limit': 18,
+ 'tags': extract_list('tags'),
+ 'categories': extract_list('categories'),
+ 'subtitles': subtitles,
}
+
+
+class PornHubPlaylistBaseIE(PornHubBaseIE):
+ def _extract_entries(self, webpage, host):
+ # Only process container div with main playlist content skipping
+ # drop-down menu that uses similar pattern for videos (see
+ # https://github.com/ytdl-org/youtube-dl/issues/11594).
+ container = self._search_regex(
+ r'(?s)(<div[^>]+class=["\']container.+)', webpage,
+ 'container', default=webpage)
+
+ return [
+ self.url_result(
+ 'http://www.%s/%s' % (host, video_url),
+ PornHubIE.ie_key(), video_title=title)
+ for video_url, title in orderedSet(re.findall(
+ r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
+ container))
+ ]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ host = mobj.group('host')
+ playlist_id = mobj.group('id')
+
+ webpage = self._download_webpage(url, playlist_id)
+
+ entries = self._extract_entries(webpage, host)
+
+ playlist = self._parse_json(
+ self._search_regex(
+ r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage,
+ 'playlist', default='{}'),
+ playlist_id, fatal=False)
+ title = playlist.get('title') or self._search_regex(
+ r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False)
+
+ return self.playlist_result(
+ entries, playlist_id, title, playlist.get('description'))
+
+
+class PornHubUserIE(PornHubPlaylistBaseIE):
+ _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?pornhub\.(?:com|net)/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/?#&]+))(?:[?#&]|/(?!videos)|$)'
+ _TESTS = [{
+ 'url': 'https://www.pornhub.com/model/zoe_ph',
+ 'playlist_mincount': 118,
+ }, {
+ 'url': 'https://www.pornhub.com/pornstar/liz-vicious',
+ 'info_dict': {
+ 'id': 'liz-vicious',
+ },
+ 'playlist_mincount': 118,
+ }, {
+ 'url': 'https://www.pornhub.com/users/russianveet69',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/channels/povd',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/model/zoe_ph?abc=1',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user_id = mobj.group('id')
+ return self.url_result(
+ '%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(),
+ video_id=user_id)
+
+
+class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ host = mobj.group('host')
+ item_id = mobj.group('id')
+
+ page = int_or_none(self._search_regex(
+ r'\bpage=(\d+)', url, 'page', default=None))
+
+ page_url = self._make_page_url(url)
+
+ entries = []
+ for page_num in (page, ) if page is not None else itertools.count(1):
+ try:
+ webpage = self._download_webpage(
+ page_url, item_id, 'Downloading page %d' % page_num,
+ query={'page': page_num})
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
+ break
+ raise
+ page_entries = self._extract_entries(webpage, host)
+ if not page_entries:
+ break
+ entries.extend(page_entries)
+ if not self._has_more(webpage):
+ break
+
+ return self.playlist_result(orderedSet(entries), item_id)
+
+
+class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
+ _VALID_URL = r'https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?P<id>(?:[^/]+/)*[^/?#&]+)'
+ _TESTS = [{
+ 'url': 'https://www.pornhub.com/model/zoe_ph/videos',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.pornhub.com/users/rushandlia/videos',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos',
+ 'info_dict': {
+ 'id': 'pornstar/jenny-blighe/videos',
+ },
+ 'playlist_mincount': 149,
+ }, {
+ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos?page=3',
+ 'info_dict': {
+ 'id': 'pornstar/jenny-blighe/videos',
+ },
+ 'playlist_mincount': 40,
+ }, {
+ # default sorting as Top Rated Videos
+ 'url': 'https://www.pornhub.com/channels/povd/videos',
+ 'info_dict': {
+ 'id': 'channels/povd/videos',
+ },
+ 'playlist_mincount': 293,
+ }, {
+ # Top Rated Videos
+ 'url': 'https://www.pornhub.com/channels/povd/videos?o=ra',
+ 'only_matching': True,
+ }, {
+ # Most Recent Videos
+ 'url': 'https://www.pornhub.com/channels/povd/videos?o=da',
+ 'only_matching': True,
+ }, {
+ # Most Viewed Videos
+ 'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
+ 'only_matching': True,
+ }, {
+ # Most Viewed Videos
+ 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=mv',
+ 'only_matching': True,
+ }, {
+ # Top Rated Videos
+ 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=tr',
+ 'only_matching': True,
+ }, {
+ # Longest Videos
+ 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=lg',
+ 'only_matching': True,
+ }, {
+ # Newest Videos
+ 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos?o=cm',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/paid',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/pornstar/liz-vicious/videos/fanonly',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/video',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/video?page=3',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/video/search?search=123',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/categories/teen',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/categories/teen?page=3',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/hd',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/hd?page=3',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/described-video',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/described-video?page=2',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/playlist/44121572',
+ 'info_dict': {
+ 'id': 'playlist/44121572',
+ },
+ 'playlist_mincount': 132,
+ }, {
+ 'url': 'https://www.pornhub.com/playlist/4667351',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://de.pornhub.com/playlist/4667351',
+ 'only_matching': True,
+ }]
+
+ @classmethod
+ def suitable(cls, url):
+ return (False
+ if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
+ else super(PornHubPagedVideoListIE, cls).suitable(url))
+
+ def _make_page_url(self, url):
+ return url
+
+ @staticmethod
+ def _has_more(webpage):
+ return re.search(
+ r'''(?x)
+ <li[^>]+\bclass=["\']page_next|
+ <link[^>]+\brel=["\']next|
+ <button[^>]+\bid=["\']moreDataBtn
+ ''', webpage) is not None
+
+
+class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
+ _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
+ _TESTS = [{
+ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
+ 'info_dict': {
+ 'id': 'jenny-blighe',
+ },
+ 'playlist_mincount': 129,
+ }, {
+ 'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
+ 'only_matching': True,
+ }]
+
+ def _make_page_url(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ return '%s/ajax' % mobj.group('url')
+
+ @staticmethod
+ def _has_more(webpage):
+ return True