X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fpornhd.py;h=27d65d4b9cdcf1e068b0d6971502eaa0caccf895;hb=56667d622c3f6e7594a04f8cd5f4371875940725;hp=7a5f00fe0b087cb6a2c298ac243e12b15daba60d;hpb=667d96480b4f9c78ceace063415c3424d4d562ea;p=youtube-dl diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index 7a5f00fe0..27d65d4b9 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -4,15 +4,32 @@ import re from .common import InfoExtractor from ..utils import ( + determine_ext, ExtractorError, int_or_none, js_to_json, + urljoin, ) class PornHdIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P\d+)(?:/(?P.+))?' - _TEST = { + _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, + } + }, { + # removed video 'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video', 'md5': '956b8ca569f7f4d8ec563e2c41598441', 'info_dict': { @@ -21,11 +38,13 @@ class PornHdIE(InfoExtractor): 'ext': 'mp4', 'title': 'Sierra loves doing laundry', 'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294', - 'thumbnail': 're:^https?://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'view_count': int, + 'like_count': int, 'age_limit': 18, - } - } + }, + 'skip': 'Not available anymore', + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -39,7 +58,7 @@ class PornHdIE(InfoExtractor): r'(.+?) - .*?[Pp]ornHD.*?'], webpage, 'title') sources = self._parse_json(js_to_json(self._search_regex( - r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]", + r"(?s)sources'?\s*[:=]\s*(\{.+?\})", webpage, 'sources', default='{}')), video_id) if not sources: @@ -50,12 +69,14 @@ class PornHdIE(InfoExtractor): formats = [] for format_id, video_url in sources.items(): + video_url = urljoin(url, video_url) if not video_url: continue height = int_or_none(self._search_regex( r'^(\d+)[pP]', format_id, 'height', default=None)) formats.append({ 'url': video_url, + 'ext': determine_ext(video_url, 'mp4'), 'format_id': format_id, 'height': height, }) @@ -67,7 +88,13 @@ class PornHdIE(InfoExtractor): view_count = int_or_none(self._html_search_regex( r'(\d+) views\s*<', webpage, 'view count', fatal=False)) thumbnail = self._search_regex( - r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False) + r"poster'?\s*:\s*([\"'])(?P(?:(?!\1).)+)\1", webpage, + 'thumbnail', fatal=False, group='url') + + like_count = int_or_none(self._search_regex( + (r'(\d+)\s*]+>(?: |\s)*\blikes', + r'class=["\']save-count["\'][^>]*>\s*(\d+)'), + webpage, 'like count', fatal=False)) return { 'id': video_id, @@ -76,6 +103,7 @@ class PornHdIE(InfoExtractor): 'description': description, 'thumbnail': thumbnail, 'view_count': view_count, + 'like_count': like_count, 'formats': formats, 'age_limit': 18, }