X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/6d835d4d6903cf5e18ad01844736929e06d16004..4ca2fce06885dfc9ee6ed3724bbf35f73ba94e29:/youtube_dl/extractor/izlesene.py diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py index 07ef682..b1d7217 100644 --- a/youtube_dl/extractor/izlesene.py +++ b/youtube_dl/extractor/izlesene.py @@ -4,12 +4,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urllib_parse_unquote from ..utils import ( - get_element_by_id, - parse_iso8601, determine_ext, - int_or_none, float_or_none, + get_element_by_id, + int_or_none, + parse_iso8601, str_to_int, ) @@ -28,9 +29,9 @@ class IzleseneIE(InfoExtractor): 'ext': 'mp4', 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', 'description': 'md5:253753e2655dde93f59f74b572454f6d', - 'thumbnail': 're:^http://.*\.jpg', + 'thumbnail': r're:^https?://.*\.jpg', 'uploader_id': 'pelikzzle', - 'timestamp': 1404298698, + 'timestamp': int, 'upload_date': '20140702', 'duration': 95.395, 'age_limit': 0, @@ -43,10 +44,9 @@ class IzleseneIE(InfoExtractor): 'id': '17997', 'ext': 'mp4', 'title': 'Tarkan Dortmund 2006 Konseri', - 'description': 'Tarkan Dortmund 2006 Konseri', - 'thumbnail': 're:^http://.*\.jpg', + 'thumbnail': r're:^https://.*\.jpg', 'uploader_id': 'parlayankiz', - 'timestamp': 1163318593, + 'timestamp': int, 'upload_date': '20061112', 'duration': 253.666, 'age_limit': 0, @@ -55,22 +55,21 @@ class IzleseneIE(InfoExtractor): ] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - url = 'http://www.izlesene.com/video/%s' % video_id + video_id = self._match_id(url) + url = 'http://www.izlesene.com/video/%s' % video_id webpage = self._download_webpage(url, video_id) title = self._og_search_title(webpage) - description = self._og_search_description(webpage) + description = self._og_search_description(webpage, default=None) thumbnail = self._proto_relative_url( self._og_search_thumbnail(webpage), scheme='http:') uploader = self._html_search_regex( r"adduserUsername\s*=\s*'([^']+)';", - webpage, 'uploader', fatal=False, default='') + webpage, 'uploader', fatal=False) timestamp = parse_iso8601(self._html_search_meta( - 'uploadDate', webpage, 'upload date', fatal=False)) + 'uploadDate', webpage, 'upload date')) duration = float_or_none(self._html_search_regex( r'"videoduration"\s*:\s*"([^"]+)"', @@ -81,17 +80,13 @@ class IzleseneIE(InfoExtractor): r'comment_count\s*=\s*\'([^\']+)\';', webpage, 'comment_count', fatal=False) - family_friendly = self._html_search_meta( - 'isFamilyFriendly', webpage, 'age limit', fatal=False) - content_url = self._html_search_meta( 'contentURL', webpage, 'content URL', fatal=False) ext = determine_ext(content_url, 'mp4') # Might be empty for some videos. streams = self._html_search_regex( - r'"qualitylevel"\s*:\s*"([^"]+)"', - webpage, 'streams', fatal=False, default='') + r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='') formats = [] if streams: @@ -99,15 +94,15 @@ class IzleseneIE(InfoExtractor): quality, url = re.search(r'\[(\w+)\](.+)', stream).groups() formats.append({ 'format_id': '%sp' % quality if quality else 'sd', - 'url': url, + 'url': compat_urllib_parse_unquote(url), 'ext': ext, }) else: stream_url = self._search_regex( - r'"streamurl"\s?:\s?"([^"]+)"', webpage, 'stream URL') + r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL') formats.append({ 'format_id': 'sd', - 'url': stream_url, + 'url': compat_urllib_parse_unquote(stream_url), 'ext': ext, }) @@ -121,6 +116,6 @@ class IzleseneIE(InfoExtractor): 'duration': duration, 'view_count': int_or_none(view_count), 'comment_count': int_or_none(comment_count), - 'age_limit': 18 if family_friendly == 'False' else 0, + 'age_limit': self._family_friendly_search(webpage), 'formats': formats, }