X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/415fdb62500dca2e22067a05008dfbf87c75b662..d317bf370d3cbd2231f3d6b1970e0a86fddc4e5b:/youtube_dl/extractor/youporn.py diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py index d456c4d..4ba7c36 100644 --- a/youtube_dl/extractor/youporn.py +++ b/youtube_dl/extractor/youporn.py @@ -6,10 +6,11 @@ import re import sys from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, - +) +from ..utils import ( ExtractorError, unescapeHTML, unified_strdate, @@ -23,7 +24,6 @@ class YouPornIE(InfoExtractor): _VALID_URL = r'^(?Phttps?://)(?:www\.)?(?Pyouporn\.com/watch/(?P[0-9]+)/(?P[^/]+))' _TEST = { 'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/', - 'md5': '71ec5fcfddacf80f495efa8b6a8d9a89', 'info_dict': { 'id': '505835', 'ext': 'mp4', @@ -46,11 +46,14 @@ class YouPornIE(InfoExtractor): age_limit = self._rta_search(webpage) # Get JSON parameters - json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, 'JSON parameters') + json_params = self._search_regex( + [r'videoJa?son\s*=\s*({.+})', + r'var\s+currentVideo\s*=\s*new\s+Video\((.+?)\)[,;]'], + webpage, 'JSON parameters') try: params = json.loads(json_params) - except: - raise ExtractorError(u'Invalid JSON') + except ValueError: + raise ExtractorError('Invalid JSON') self.report_extraction(video_id) try: @@ -65,7 +68,7 @@ class YouPornIE(InfoExtractor): # Get all of the links from the page DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>' download_list_html = self._search_regex(DOWNLOAD_LIST_RE, - webpage, 'download list').strip() + webpage, 'download list').strip() LINK_RE = r'<a href="([^"]+)">' links = re.findall(LINK_RE, download_list_html) @@ -74,7 +77,7 @@ class YouPornIE(InfoExtractor): for encrypted_link in encrypted_links: link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8') links.append(link) - + formats = [] for link in links: # A link looks like this: @@ -104,8 +107,8 @@ class YouPornIE(InfoExtractor): self._sort_formats(formats) if not formats: - raise ExtractorError(u'ERROR: no known formats available for video') - + raise ExtractorError('ERROR: no known formats available for video') + return { 'id': video_id, 'uploader': video_uploader,