X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/0865c28fb29a6481cd837cf8c1ef0cd134c6ef8e..bbf0d3ad085e9b9fdee0b06a32d303becf0df916:/youtube_dl/extractor/pornhd.py diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py index dbb2c3b..842317e 100644 --- a/youtube_dl/extractor/pornhd.py +++ b/youtube_dl/extractor/pornhd.py @@ -1,19 +1,32 @@ from __future__ import unicode_literals import re -import json from .common import InfoExtractor from ..utils import ( + ExtractorError, int_or_none, js_to_json, - qualities, ) class PornHdIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P\d+)(?:/(?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': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5', + '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, + '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': { @@ -22,11 +35,12 @@ 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, 'age_limit': 18, - } - } + }, + 'skip': 'Not available anymore', + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -36,29 +50,40 @@ class PornHdIE(InfoExtractor): webpage = self._download_webpage(url, display_id or video_id) title = self._html_search_regex( - r'(.+) porn HD.+?', webpage, 'title') - description = self._html_search_regex( - r'
([^<]+)
', webpage, 'description', fatal=False) - 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']+class=["\']video-name["\'][^>]*>([^<]+)', + r'(.+?) - .*?[Pp]ornHD.*?'], webpage, 'title') - quality = qualities(['sd', 'hd']) - sources = json.loads(js_to_json(self._search_regex( + sources = self._parse_json(js_to_json(self._search_regex( r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]", - webpage, 'sources'))) + webpage, 'sources', default='{}')), video_id) + + if not sources: + message = self._html_search_regex( + r'(?s)<(div|p)[^>]+class="no-video"[^>]*>(?P.+?)]+class="description"[^>]*>(?P[^<]+)