X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/af478477605bdf3f5d57562035885cfee905f379..8593410c28e395b68b410169356663541005c3ae:/youtube_dl/extractor/pornhd.py?ds=inline diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 58f9c69..c6052ac 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -3,42 +3,119 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import compat_urllib_parse +from ..utils import ( + determine_ext, + ExtractorError, + int_or_none, + js_to_json, + merge_dicts, + urljoin, +) class PornHdIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P[0-9]+)/(?P.+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P\d+)(?:/(?P.+))?' + _TESTS = [{ + 'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video', + 'md5': '87f1540746c1d32ec7a2305c12b96b25', + 'info_dict': { + 'id': '9864', + 'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video', + 'ext': 'mp4', + 'title': 'Restroom selfie masturbation', + 'description': 'md5:3748420395e03e31ac96857a8f125b2b', + 'thumbnail': r're:^https?://.*\.jpg', + 'view_count': int, + 'like_count': int, + 'age_limit': 18, + }, + 'skip': 'HTTP Error 404: Not Found', + }, { 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', - 'file': '1962.flv', - 'md5': '35272469887dca97abd30abecc6cdf75', + 'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de', 'info_dict': { - "title": "sierra-day-gets-his-cum-all-over-herself-hd-porn-video", - "age_limit": 18, - } - } + 'id': '1962', + 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', + 'ext': 'mp4', + 'title': 'md5:98c6f8b2d9c229d0f0fde47f61a1a759', + 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', + 'thumbnail': r're:^https?://.*\.jpg', + 'view_count': int, + 'like_count': int, + 'age_limit': 18, + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id or video_id) + + title = self._html_search_regex( + [r']+class=["\']video-name["\'][^>]*>([^<]+)', + r'(.+?) - .*?[Pp]ornHD.*?'], webpage, 'title') + + sources = self._parse_json(js_to_json(self._search_regex( + r"(?s)sources'?\s*[:=]\s*(\{.+?\})", + webpage, 'sources', default='{}')), video_id) + + info = {} + if not sources: + entries = self._parse_html5_media_entries(url, webpage, video_id) + if entries: + info = entries[0] - video_id = mobj.group('video_id') - video_title = mobj.group('video_title') + if not sources and not info: + message = self._html_search_regex( + r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P.+?)]+class=["\']video-description[^>]+>(?P.+?)', + r'<(div|p)[^>]+class="description"[^>]*>(?P[^<]+)(?:(?!\1).)+)\1", webpage, + 'thumbnail', default=None, group='url') - video_url = self._download_webpage( - next_url, video_id, note='Retrieving video URL', - errnote='Could not retrieve video URL') - age_limit = 18 + like_count = int_or_none(self._search_regex( + (r'(\d+)\s*likes', + r'(\d+)\s*]+>(?: |\s)*\blikes', + r'class=["\']save-count["\'][^>]*>\s*(\d+)'), + webpage, 'like count', fatal=False)) - return { + return merge_dicts(info, { 'id': video_id, - 'url': video_url, - 'ext': 'flv', - 'title': video_title, - 'age_limit': age_limit, - } + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'view_count': view_count, + 'like_count': like_count, + 'formats': formats, + 'age_limit': 18, + })