X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/c512650955de0b16d37e7fa7fb29ea0985e415bb..bb0545d1ede66375ab242a96da748913992bbf0d:/youtube_dl/extractor/pornhd.py?ds=inline diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 718fe9a..c6052ac 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -1,81 +1,121 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor -from ..utils import int_or_none +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\d+)' - _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', - 'md5': '956b8ca569f7f4d8ec563e2c41598441', + 'md5': '1b7b3a40b9d65a8e5b25f7ab9ee6d6de', 'info_dict': { 'id': '1962', + 'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'ext': 'mp4', - 'title': 'Sierra loves doing laundry', + '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, video_id) + webpage = self._download_webpage(url, display_id or video_id) - title = self._og_search_title(webpage) - TITLE_SUFFIX = ' porn HD Video | PornHD.com ' - if title.endswith(TITLE_SUFFIX): - title = title[:-len(TITLE_SUFFIX)] + title = self._html_search_regex( + [r']+class=["\']video-name["\'][^>]*>([^<]+)', + r'(.+?) - .*?[Pp]ornHD.*?'], webpage, 'title') - description = self._html_search_regex( - r'
([^<]+)
', webpage, 'description', fatal=False) - view_count = int_or_none(self._html_search_regex( - r'(\d+) views ', webpage, 'view count', fatal=False)) + sources = self._parse_json(js_to_json(self._search_regex( + r"(?s)sources'?\s*[:=]\s*(\{.+?\})", + webpage, 'sources', default='{}')), video_id) - formats = [ - { - 'url': format_url, - 'ext': format.lower(), - 'format_id': '%s-%s' % (format.lower(), quality.lower()), - 'quality': 1 if quality.lower() == 'high' else 0, - } for format, quality, format_url in re.findall( - r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage) - ] + info = {} + if not sources: + entries = self._parse_html5_media_entries(url, webpage, video_id) + if entries: + info = entries[0] - mobj = re.search(r'flashVars = (?P{.+?});', webpage) - if mobj: - flashvars = json.loads(mobj.group('flashvars')) - formats.extend([ - { - 'url': flashvars['hashlink'].replace('?noProxy=1', ''), - 'ext': 'flv', - 'format_id': 'flv-low', - 'quality': 0, - }, - { - 'url': flashvars['hd'].replace('?noProxy=1', ''), - 'ext': 'flv', - 'format_id': 'flv-high', - 'quality': 1, - } - ]) - thumbnail = flashvars['urlWallpaper'] - else: - thumbnail = self._og_search_thumbnail(webpage) + 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') - self._sort_formats(formats) + 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, + 'display_id': display_id, 'title': title, 'description': description, 'thumbnail': thumbnail, 'view_count': view_count, + 'like_count': like_count, 'formats': formats, 'age_limit': 18, - } + })