X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fspankwire.py;h=3362b3db85c65c97d8839d8707e36fecf8bc6646;hb=c4db377cbb25c35c0e9df95f275d439cff75a770;hp=f0d5009c717be0cd02ea7edf2b74af0a7a8e8b80;hpb=82f0ac657c0399659863b0bdec3afea2020ca5a9;p=youtube-dl diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py index f0d5009c7..3362b3db8 100644 --- a/youtube_dl/extractor/spankwire.py +++ b/youtube_dl/extractor/spankwire.py @@ -1,3 +1,5 @@ +from __future__ import unicode_literals + import os import re @@ -6,22 +8,23 @@ from ..utils import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, - unescapeHTML, ) from ..aes import ( aes_decrypt_text ) + class SpankwireIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pspankwire\.com/[^/]*/video(?P[0-9]+)/?)' _TEST = { - u'url': u'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/', - u'file': u'103545.mp4', - u'md5': u'1b3f55e345500552dbc252a3e9c1af43', - u'info_dict': { - u"uploader": u"oreusz", - u"title": u"Buckcherry`s X Rated Music Video Crazy Bitch", - u"description": u"Crazy Bitch X rated music video.", + 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/', + 'file': '103545.mp4', + 'md5': '1b3f55e345500552dbc252a3e9c1af43', + 'info_dict': { + "uploader": "oreusz", + "title": "Buckcherry`s X Rated Music Video Crazy Bitch", + "description": "Crazy Bitch X rated music video.", + "age_limit": 18, } } @@ -34,31 +37,41 @@ class SpankwireIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'

([^<]+)', webpage, u'title') - video_uploader = self._html_search_regex(r'by:\s*]*>(.+?)', webpage, u'uploader', fatal=False) - thumbnail = self._html_search_regex(r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False) - description = self._html_search_regex(r'>\s*Description:\s*<[^>]*>([^<]+)', webpage, u'description', fatal=False) - if len(description) == 0: - description = None + video_title = self._html_search_regex(r'

([^<]+)', webpage, 'title') + video_uploader = self._html_search_regex( + r'by:\s*]*>(.+?)', webpage, 'uploader', fatal=False) + thumbnail = self._html_search_regex( + r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False) + description = self._html_search_regex( + r'([^<]+)<', webpage, 'description', fatal=False) video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage))) if webpage.find('flashvars\.encrypted = "true"') != -1: - password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, u'password').replace('+', ' ') + password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ') video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls)) formats = [] for video_url in video_urls: - path = compat_urllib_parse_urlparse( video_url ).path - extension = os.path.splitext( path )[1][1:] + path = compat_urllib_parse_urlparse(video_url).path + extension = os.path.splitext(path)[1][1:] format = path.split('/')[4].split('_')[:2] - format = "-".join( format ) + resolution, bitrate_str = format + format = "-".join(format) + height = int(resolution.rstrip('P')) + tbr = int(bitrate_str.rstrip('K')) + formats.append({ 'url': video_url, 'ext': extension, + 'resolution': resolution, 'format': format, + 'tbr': tbr, + 'height': height, 'format_id': format, }) - formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-')))) + self._sort_formats(formats) + + age_limit = self._rta_search(webpage) return { 'id': video_id, @@ -67,4 +80,5 @@ class SpankwireIE(InfoExtractor): 'thumbnail': thumbnail, 'description': description, 'formats': formats, + 'age_limit': age_limit, }