+# coding: utf-8
from __future__ import unicode_literals
+import itertools
import os
import re
from .common import InfoExtractor
from ..compat import (
+ compat_HTTPError,
compat_urllib_parse_unquote,
compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlparse,
)
from ..utils import (
ExtractorError,
+ int_or_none,
+ orderedSet,
sanitized_Request,
str_to_int,
)
class PornHubIE(InfoExtractor):
- _VALID_URL = r'https?://(?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)(?P<id>[0-9a-z]+)'
+ IE_DESC = 'PornHub and Thumbzilla'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:[a-z]+\.)?pornhub\.com/(?:view_video\.php\?viewkey=|embed/)|
+ (?:www\.)?thumbzilla\.com/video/
+ )
+ (?P<id>[0-9a-z]+)
+ '''
_TESTS = [{
'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015',
- 'md5': '882f488fa1f0026f023f33576004a2ed',
+ 'md5': '1e19b41231a02eba417839222ac9d58e',
'info_dict': {
'id': '648719015',
'ext': 'mp4',
- 'uploader': 'Babes',
'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
- 'age_limit': 18
- }
+ 'uploader': 'Babes',
+ 'duration': 361,
+ 'view_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'comment_count': int,
+ 'age_limit': 18,
+ },
+ }, {
+ # 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': 'cj397186295',
+ 'duration': 1753,
+ 'view_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'comment_count': int,
+ 'age_limit': 18,
+ },
+ '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,
}]
@classmethod
webpage = self._download_webpage(req, video_id)
error_msg = self._html_search_regex(
- r'(?s)<div class="userMessageSection[^"]*".*?>(.*?)</div>',
- webpage, 'error message', default=None)
+ r'(?s)<div[^>]+class=(["\']).*?\b(?:removed|userMessageSection)\b.*?\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)
- video_title = self._html_search_regex(r'<h1 [^>]+>([^<]+)', webpage, 'title')
+ # 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')
+
+ flashvars = self._parse_json(
+ self._search_regex(
+ r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
+ video_id)
+ if flashvars:
+ thumbnail = flashvars.get('image_url')
+ duration = int_or_none(flashvars.get('video_duration'))
+ else:
+ title, thumbnail, duration = [None] * 3
+
video_uploader = self._html_search_regex(
r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|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)
view_count = self._extract_count(
r'<span class="count">([\d,\.]+)</span> views', webpage, 'view')
return {
'id': video_id,
'uploader': video_uploader,
- 'title': video_title,
+ 'title': title,
'thumbnail': thumbnail,
+ 'duration': duration,
'view_count': view_count,
'like_count': like_count,
'dislike_count': dislike_count,
class PornHubPlaylistBaseIE(InfoExtractor):
def _extract_entries(self, webpage):
return [
- self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
- for video_url in set(re.findall(
- r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage))
+ self.url_result(
+ 'http://www.pornhub.com/%s' % 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="([^"]+)"',
+ webpage))
]
def _real_extract(self, url):
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
_VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
_TESTS = [{
- 'url': 'http://www.pornhub.com/users/rushandlia/videos',
+ 'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'info_dict': {
- 'id': 'rushandlia',
+ 'id': 'zoe_ph',
},
- 'playlist_mincount': 13,
+ 'playlist_mincount': 171,
+ }, {
+ 'url': 'http://www.pornhub.com/users/rushandlia/videos',
+ 'only_matching': True,
}]
def _real_extract(self, url):
user_id = self._match_id(url)
- webpage = self._download_webpage(url, user_id)
+ entries = []
+ for page_num in itertools.count(1):
+ try:
+ webpage = self._download_webpage(
+ url, user_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
+ page_entries = self._extract_entries(webpage)
+ if not page_entries:
+ break
+ entries.extend(page_entries)
- return self.playlist_result(self._extract_entries(webpage), user_id)
+ return self.playlist_result(entries, user_id)
projects / youtube-dl / blobdiff