From 93f3f10cdcf40bdeb6c61b36bbbc0d0ab45ba66c Mon Sep 17 00:00:00 2001 From: Remita Amine Date: Sat, 25 Nov 2017 19:28:26 +0100 Subject: [PATCH] [fczenit] fix extraction --- youtube_dl/extractor/fczenit.py | 40 ++++++++++++++++++++------------- 1 file changed, 24 insertions(+), 16 deletions(-) diff --git a/youtube_dl/extractor/fczenit.py b/youtube_dl/extractor/fczenit.py index 8d1010b88..8db7c5963 100644 --- a/youtube_dl/extractor/fczenit.py +++ b/youtube_dl/extractor/fczenit.py @@ -2,7 +2,10 @@ from __future__ import unicode_literals from .common import InfoExtractor -from ..compat import compat_urlparse +from ..utils import ( + int_or_none, + float_or_none, +) class FczenitIE(InfoExtractor): @@ -14,6 +17,8 @@ class FczenitIE(InfoExtractor): 'id': '41044', 'ext': 'mp4', 'title': 'Так пишется история: казанский разгром ЦСКА на «Зенит-ТВ»', + 'timestamp': 1462283735, + 'upload_date': '20160503', }, } @@ -21,28 +26,31 @@ def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) - video_title = self._html_search_regex( - r'<[^>]+class=\"photoalbum__title\">([^<]+)', webpage, 'title') + msi_id = self._search_regex( + r"(?s)config\s*=\s*{.+?video_id\s*:\s*'([^']+)'", webpage, 'msi id') - video_items = self._parse_json(self._search_regex( - r'arrPath\s*=\s*JSON\.parse\(\'(.+)\'\)', webpage, 'video items'), - video_id) - - def merge_dicts(*dicts): - ret = {} - for a_dict in dicts: - ret.update(a_dict) - return ret + msi_data = self._download_json( + 'http://player.fc-zenit.ru/msi/video', msi_id, query={ + 'video': msi_id, + })['data'] + title = msi_data['name'] formats = [{ - 'url': compat_urlparse.urljoin(url, video_url), - 'tbr': int(tbr), - } for tbr, video_url in merge_dicts(*video_items).items()] + 'format_id': q.get('label'), + 'url': q['url'], + 'height': int_or_none(q.get('label')), + } for q in msi_data['qualities'] if q.get('url')] self._sort_formats(formats) + tags = [tag['label'] for tag in msi_data.get('tags', []) if tag.get('label')] + return { 'id': video_id, - 'title': video_title, + 'title': title, + 'thumbnail': msi_data.get('preview'), 'formats': formats, + 'duration': float_or_none(msi_data.get('duration')), + 'timestamp': int_or_none(msi_data.get('date')), + 'tags': tags, }