From 7fadcf71c6b6f9bd1cfb662b3bc1b7d8af444f46 Mon Sep 17 00:00:00 2001 From: remitamine Date: Sat, 3 Oct 2015 16:05:29 +0100 Subject: [PATCH] [izlesene] extract info using api request --- youtube_dl/extractor/izlesene.py | 68 ++++++-------------------------- 1 file changed, 13 insertions(+), 55 deletions(-) diff --git a/youtube_dl/extractor/izlesene.py b/youtube_dl/extractor/izlesene.py index bc226fa67..a56162d04 100644 --- a/youtube_dl/extractor/izlesene.py +++ b/youtube_dl/extractor/izlesene.py @@ -6,11 +6,7 @@ import re from .common import InfoExtractor 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, ) @@ -28,13 +24,8 @@ class IzleseneIE(InfoExtractor): 'id': '7599694', 'ext': 'mp4', 'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi', - 'description': 'md5:253753e2655dde93f59f74b572454f6d', 'thumbnail': 're:^http://.*\.jpg', - 'uploader_id': 'pelikzzle', - 'timestamp': int, - 'upload_date': '20140702', - 'duration': 95.395, - 'age_limit': 0, + 'duration': 95395, } }, { @@ -44,13 +35,8 @@ class IzleseneIE(InfoExtractor): 'id': '17997', 'ext': 'mp4', 'title': 'Tarkan Dortmund 2006 Konseri', - 'description': 'Tarkan Dortmund 2006 Konseri', 'thumbnail': 're:^http://.*\.jpg', - 'uploader_id': 'parlayankiz', - 'timestamp': int, - 'upload_date': '20061112', - 'duration': 253.666, - 'age_limit': 0, + 'duration': 253666, } }, ] @@ -58,65 +44,37 @@ class IzleseneIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - url = 'http://www.izlesene.com/video/%s' % video_id - webpage = self._download_webpage(url, video_id) + api_data = self._download_json('http://panel.izlesene.com/api/playerJson/izlesene/%s' % video_id, video_id) - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - 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, 'mp4') + title = api_data['videoname'] + thumbnail = api_data.get('thumbnail') + duration = int_or_none(api_data.get('videoduration')) + view_count = int_or_none(str_to_int(api_data.get('views'))) # Might be empty for some videos. - streams = self._html_search_regex( - r'"qualitylevel"\s*:\s*"([^"]+)"', webpage, 'streams', default='') + streams = api_data.get('qualitylevel') formats = [] + # TODO: extract formats from dash manifest 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, + 'url': url, }) else: - stream_url = self._search_regex( - r'"streamurl"\s*:\s*"([^"]+)"', webpage, 'stream URL') + stream_url = api_data.get('streamurl') formats.append({ 'format_id': 'sd', - 'url': compat_urllib_parse_unquote(stream_url), - 'ext': ext, + 'url': stream_url, }) return { 'id': video_id, 'title': title, - 'description': description, 'thumbnail': thumbnail, - 'uploader_id': uploader, - 'timestamp': timestamp, 'duration': duration, - 'view_count': int_or_none(view_count), - 'comment_count': int_or_none(comment_count), - 'age_limit': self._family_friendly_search(webpage), + 'view_count': view_count, 'formats': formats, }