X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/46113edab215c2211a604c06245c16d5d4e57dcf..d904ce9fca517ea1b6310e731acddcdd05dda618:/youtube_dl/extractor/pornhub.py diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index 618e8f5..0c8b731 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -4,10 +4,13 @@ import os import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( + compat_urllib_parse, compat_urllib_parse_urlparse, compat_urllib_request, - compat_urllib_parse, +) +from ..utils import ( + ExtractorError, str_to_int, ) from ..aes import ( @@ -16,7 +19,7 @@ from ..aes import ( class PornHubIE(InfoExtractor): - _VALID_URL = r'^https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P[0-9a-f]+)' + _VALID_URL = r'https?://(?:www\.)?pornhub\.com/view_video\.php\?viewkey=(?P[0-9a-f]+)' _TEST = { 'url': 'http://www.pornhub.com/view_video.php?viewkey=648719015', 'md5': '882f488fa1f0026f023f33576004a2ed', @@ -30,10 +33,8 @@ class PornHubIE(InfoExtractor): } 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): video_id = self._match_id(url) @@ -42,21 +43,33 @@ class PornHubIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) + error_msg = self._html_search_regex( + r'(?s)
(.*?)
', + webpage, 'error message', default=None) + 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'

]+>([^<]+)', webpage, 'title') video_uploader = self._html_search_regex( - r'(?s)From: .+?<(?:a href="/users/|a href="/channels/|]+>(.+?)<', 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'([\d,\.]+) views', webpage, 'view') - like_count = self._extract_count(r'([\d,\.]+)', webpage, 'like') - dislike_count = self._extract_count(r'([\d,\.]+)', webpage, 'dislike') + view_count = self._extract_count( + r'([\d,\.]+) views', webpage, 'view') + like_count = self._extract_count( + r'([\d,\.]+)', webpage, 'like') + dislike_count = self._extract_count( + r'([\d,\.]+)', webpage, 'dislike') comment_count = self._extract_count( - r'All comments \(([\d,\.]+)', webpage, 'comment') + r'All Comments\s*\(([\d,.]+)\)', webpage, 'comment') - video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'"quality_[0-9]{3}p":"([^"]+)', webpage))) + 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)) @@ -98,3 +111,33 @@ class PornHubIE(InfoExtractor): 'formats': formats, 'age_limit': 18, } + + +class PornHubPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P\d+)' + _TESTS = [{ + 'url': 'http://www.pornhub.com/playlist/6201671', + 'info_dict': { + 'id': '6201671', + 'title': 'P0p4', + }, + 'playlist_mincount': 35, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [ + self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub') + for video_url in set(re.findall('href="/?(view_video\.php\?viewkey=\d+[^"]*)"', webpage)) + ] + + playlist = self._parse_json( + self._search_regex( + r'playlistObject\s*=\s*({.+?});', webpage, 'playlist'), + playlist_id) + + return self.playlist_result( + entries, playlist_id, playlist.get('title'), playlist.get('description'))