X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fizlesene.py;h=b1d72177d5acef2c48a82f7df18081005199b47e;hb=54fc90aabfb71968f28af68dfe3f7a3544cc2f0b;hp=e51358595db67412919a77a576a38436721f6343;hpb=366b1f3cfe9993dfdd80116fcf8a91b7a3eff75d;p=youtube-dl diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py index e51358595..b1d72177d 100644 --- a/youtube_dl/extractor/izlesene.py +++ b/youtube_dl/extractor/izlesene.py @@ -4,91 +4,118 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import get_element_by_id, parse_iso8601, determine_ext, int_or_none +from ..compat import compat_urllib_parse_unquote +from ..utils import ( + determine_ext, + float_or_none, + get_element_by_id, + int_or_none, + parse_iso8601, + str_to_int, +) class IzleseneIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.|m\.)?izlesene\.com/(?:video|embedplayer)/(?:[^/]+/)?(?P[0-9]+)' - _STREAM_URL = 'http://panel.izlesene.com/api/streamurl/{id:}/{format:}' - _TEST = { - 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', - 'md5': '4384f9f0ea65086734b881085ee05ac2', - 'info_dict': { - 'id': '7599694', - 'title': u'Sevinçten Çıldırtan Doğum Günü Hediyesi', - 'upload_date': '20140702', - 'uploader_id': 'pelikzzle', - 'description': u'Annesi oğluna doğum günü hediyesi olarak minecraft cd si alıyor, ve çocuk hunharca seviniyor', - 'timestamp': 1404298698, - 'duration': 95, - 'ext': 'mp4', - 'thumbnail': 're:^http://.*\.jpg', - 'age_limit': 0, - } - } + _VALID_URL = r'''(?x) + https?://(?:(?:www|m)\.)?izlesene\.com/ + (?:video|embedplayer)/(?:[^/]+/)?(?P[0-9]+) + ''' + _TESTS = [ + { + 'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694', + 'md5': '4384f9f0ea65086734b881085ee05ac2', + 'info_dict': { + 'id': '7599694', + 'ext': 'mp4', + 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', + 'description': 'md5:253753e2655dde93f59f74b572454f6d', + 'thumbnail': r're:^https?://.*\.jpg', + 'uploader_id': 'pelikzzle', + 'timestamp': int, + 'upload_date': '20140702', + 'duration': 95.395, + 'age_limit': 0, + } + }, + { + 'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997', + 'md5': '97f09b6872bffa284cb7fa4f6910cb72', + 'info_dict': { + 'id': '17997', + 'ext': 'mp4', + 'title': 'Tarkan Dortmund 2006 Konseri', + 'thumbnail': r're:^https://.*\.jpg', + 'uploader_id': 'parlayankiz', + 'timestamp': int, + 'upload_date': '20061112', + 'duration': 253.666, + 'age_limit': 0, + } + }, + ] 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) - thumbnail = self._og_search_thumbnail(webpage) - duration = int( - self._html_search_regex( - r'"videoduration"\s?:\s?"([^"]+)"', webpage, 'duration', - fatal=False, default='0') - ) / 1000 - view_count = get_element_by_id('videoViewCount', - webpage).replace('.', '') - timestamp = parse_iso8601(self._html_search_meta('uploadDate', webpage, - 'upload date', fatal=False)) - family_friendly = self._html_search_meta('isFamilyFriendly', webpage, - 'age limit', fatal=False) - uploader = self._html_search_regex(r"adduserUsername\s?=\s?'([^']+)';", - webpage, 'uploader', fatal=False, - default='') - comment_count = self._html_search_regex( - r'comment_count\s?=\s?\'([^\']+)\';', + 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) + timestamp = parse_iso8601(self._html_search_meta( + 'uploadDate', webpage, 'upload date')) + + duration = float_or_none(self._html_search_regex( + r'"videoduration"\s*:\s*"([^"]+)"', + webpage, 'duration', fatal=False), scale=1000) + + view_count = str_to_int(get_element_by_id('videoViewCount', webpage)) + comment_count = self._html_search_regex( + r'comment_count\s*=\s*\'([^\']+)\';', + webpage, 'comment_count', fatal=False) - content_url = self._html_search_meta('contentURL', webpage, - 'content URL', fatal=False) - ext = determine_ext(content_url) + content_url = self._html_search_meta( + 'contentURL', webpage, 'content URL', fatal=False) + ext = determine_ext(content_url, 'mp4') # Might be empty for some videos. - qualities = self._html_search_regex(r'"quality"\s?:\s?"([^"]+)"', - webpage, 'qualities', fatal=False, - default='') + streams = self._html_search_regex( + r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='') formats = [] - for quality in qualities.split('|'): - json = self._download_json( - self._STREAM_URL.format(id=video_id, format=quality), video_id, - note=u'Getting video URL for "%s" quality' % quality, - errnote=u'Failed to get video URL for "%s" quality' % quality - ) - video_format = '%sp' % quality if quality else 'sd' + if streams: + for stream in streams.split('|'): + quality, url = re.search(r'\[(\w+)\](.+)', stream).groups() + formats.append({ + 'format_id': '%sp' % quality if quality else 'sd', + 'url': compat_urllib_parse_unquote(url), + 'ext': ext, + }) + else: + stream_url = self._search_regex( + r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL') formats.append({ - 'url': json.get('streamurl'), + 'format_id': 'sd', + 'url': compat_urllib_parse_unquote(stream_url), 'ext': ext, - 'format': video_format, - 'format_id': video_format, }) return { 'id': video_id, 'title': title, - 'formats': formats, 'description': description, 'thumbnail': thumbnail, + 'uploader_id': uploader, + 'timestamp': timestamp, 'duration': duration, 'view_count': int_or_none(view_count), - 'timestamp': timestamp, - 'age_limit': 18 if family_friendly == 'False' else 0, - 'uploader_id': uploader, 'comment_count': int_or_none(comment_count), + 'age_limit': self._family_friendly_search(webpage), + 'formats': formats, }