X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fizlesene.py;h=f8fca6c8f47c9978e78d1c2c76d0dcb84a8d7f9d;hb=HEAD;hp=e51358595db67412919a77a576a38436721f6343;hpb=328a20bf9c9cbc67ad0d4147bae0292cf2aec64b;p=youtube-dl diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py index e51358595..f8fca6c8f 100644 --- a/youtube_dl/extractor/izlesene.py +++ b/youtube_dl/extractor/izlesene.py @@ -1,94 +1,117 @@ # coding: utf-8 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_str, + 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 - - webpage = self._download_webpage(url, video_id) + video_id = self._match_id(url) - 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?\'([^\']+)\';', - webpage, 'uploader', fatal=False) + webpage = self._download_webpage('http://www.izlesene.com/video/%s' % video_id, video_id) - content_url = self._html_search_meta('contentURL', webpage, - 'content URL', fatal=False) - ext = determine_ext(content_url) + video = self._parse_json( + self._search_regex( + r'videoObj\s*=\s*({.+?})\s*;\s*\n', webpage, 'streams'), + video_id) - # Might be empty for some videos. - qualities = self._html_search_regex(r'"quality"\s?:\s?"([^"]+)"', - webpage, 'qualities', fatal=False, - default='') + title = video.get('videoTitle') or self._og_search_title(webpage) 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' + for stream in video['media']['level']: + source_url = stream.get('source') + if not source_url or not isinstance(source_url, compat_str): + continue + ext = determine_ext(url, 'mp4') + quality = stream.get('value') + height = int_or_none(quality) formats.append({ - 'url': json.get('streamurl'), + 'format_id': '%sp' % quality if quality else 'sd', + 'url': compat_urllib_parse_unquote(source_url), 'ext': ext, - 'format': video_format, - 'format_id': video_format, + 'height': height, }) + self._sort_formats(formats) + + description = self._og_search_description(webpage, default=None) + thumbnail = video.get('posterURL') or 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(video.get('duration') or self._html_search_regex( + r'videoduration["\']?\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', + webpage, 'duration', fatal=False, group='value'), 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) 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, }