X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Feporner.py;h=bb231ecb1cd81577d41c9c16ec3e0156c4abcf3e;hb=5a000b45b339f6516f2a5a3bdfd2869713e8438a;hp=4c2c074cbcf0c13a147ab1e0856bb0e8f6efc1d9;hpb=329818484ce44229835f4b2b02006120b0d81bcf;p=youtube-dl diff --git a/youtube_dl/extractor/eporner.py b/youtube_dl/extractor/eporner.py index 4c2c074cb..bb231ecb1 100644 --- a/youtube_dl/extractor/eporner.py +++ b/youtube_dl/extractor/eporner.py @@ -11,23 +11,27 @@ from ..utils import ( class EpornerIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P\d+)/(?P[\w-]+)/?' + _VALID_URL = r'https?://(?:www\.)?eporner\.com/hd-porn/(?P\d+)/(?P[\w-]+)' _TEST = { 'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/', - 'md5': '3b427ae4b9d60619106de3185c2987cd', + 'md5': '39d486f046212d8e1b911c52ab4691f8', 'info_dict': { 'id': '95008', - 'ext': 'flv', + 'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video', + 'ext': 'mp4', 'title': 'Infamous Tiffany Teen Strip Tease Video', 'duration': 194, 'view_count': int, + 'age_limit': 18, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') - webpage = self._download_webpage(url, video_id) + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) title = self._html_search_regex( r'(.*?) - EPORNER', webpage, 'title') @@ -35,9 +39,23 @@ class EpornerIE(InfoExtractor): r'<script type="text/javascript" src="/config5/%s/([a-f\d]+)/">' % video_id, webpage, 'redirect_code') redirect_url = 'http://www.eporner.com/config5/%s/%s' % (video_id, redirect_code) - webpage2 = self._download_webpage(redirect_url, video_id) - video_url = self._html_search_regex( - r'file: "(.*?)",', webpage2, 'video_url') + player_code = self._download_webpage( + redirect_url, display_id, note='Downloading player config') + + sources = self._search_regex( + r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', player_code, 'sources') + + formats = [] + for video_url, format_id in re.findall(r'file\s*:\s*"([^"]+)",\s*label\s*:\s*"([^"]+)"', sources): + fmt = { + 'url': video_url, + 'format_id': format_id, + } + m = re.search(r'^(\d+)', format_id) + if m: + fmt['height'] = int(m.group(1)) + formats.append(fmt) + self._sort_formats(formats) duration = parse_duration(self._search_regex( r'class="mbtim">([0-9:]+)</div>', webpage, 'duration', @@ -48,8 +66,10 @@ class EpornerIE(InfoExtractor): return { 'id': video_id, - 'url': video_url, + 'display_id': display_id, 'title': title, 'duration': duration, 'view_count': view_count, + 'formats': formats, + 'age_limit': self._rta_search(webpage), }