From 87b5184a0d7e32f595fca19b1ec227164ccd0acd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Wed, 31 May 2017 23:56:32 +0700 Subject: [PATCH] [drbonanza] Fix extraction (closes #13231) --- youtube_dl/extractor/drbonanza.py | 146 +++++++----------------------- 1 file changed, 35 insertions(+), 111 deletions(-) diff --git a/youtube_dl/extractor/drbonanza.py b/youtube_dl/extractor/drbonanza.py index 79ec212c8..164e97c36 100644 --- a/youtube_dl/extractor/drbonanza.py +++ b/youtube_dl/extractor/drbonanza.py @@ -1,135 +1,59 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor from ..utils import ( - int_or_none, - parse_iso8601, + js_to_json, + parse_duration, + unescapeHTML, ) class DRBonanzaIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/(?:[^/]+/)+(?:[^/])+?(?:assetId=(?P\d+))?(?:[#&]|$)' - - _TESTS = [{ - 'url': 'http://www.dr.dk/bonanza/serie/portraetter/Talkshowet.htm?assetId=65517', + _VALID_URL = r'https?://(?:www\.)?dr\.dk/bonanza/[^/]+/\d+/[^/]+/(?P\d+)/(?P[^/?#&]+)' + _TEST = { + 'url': 'http://www.dr.dk/bonanza/serie/154/matador/40312/matador---0824-komme-fremmede-', 'info_dict': { - 'id': '65517', + 'id': '40312', + 'display_id': 'matador---0824-komme-fremmede-', 'ext': 'mp4', - 'title': 'Talkshowet - Leonard Cohen', - 'description': 'md5:8f34194fb30cd8c8a30ad8b27b70c0ca', + 'title': 'MATADOR - 08:24. "Komme fremmede".', + 'description': 'md5:77b4c1ac4d4c1b9d610ab4395212ff84', 'thumbnail': r're:^https?://.*\.(?:gif|jpg)$', - 'timestamp': 1295537932, - 'upload_date': '20110120', - 'duration': 3664, + 'duration': 4613, }, - 'params': { - 'skip_download': True, # requires rtmp - }, - }, { - 'url': 'http://www.dr.dk/bonanza/radio/serie/sport/fodbold.htm?assetId=59410', - 'md5': '6dfe039417e76795fb783c52da3de11d', - 'info_dict': { - 'id': '59410', - 'ext': 'mp3', - 'title': 'EM fodbold 1992 Danmark - Tyskland finale Transmission', - 'description': 'md5:501e5a195749480552e214fbbed16c4e', - 'thumbnail': r're:^https?://.*\.(?:gif|jpg)$', - 'timestamp': 1223274900, - 'upload_date': '20081006', - 'duration': 7369, - }, - }] + } def _real_extract(self, url): - url_id = self._match_id(url) - webpage = self._download_webpage(url, url_id) + mobj = re.match(self._VALID_URL, url) + video_id, display_id = mobj.group('id', 'display_id') - if url_id: - info = json.loads(self._html_search_regex(r'({.*?%s.*})' % url_id, webpage, 'json')) - else: - # Just fetch the first video on that page - info = json.loads(self._html_search_regex(r'bonanzaFunctions.newPlaylist\(({.*})\)', webpage, 'json')) + webpage = self._download_webpage(url, display_id) - asset_id = str(info['AssetId']) - title = info['Title'].rstrip(' \'\"-,.:;!?') - duration = int_or_none(info.get('Duration'), scale=1000) - # First published online. "FirstPublished" contains the date for original airing. - timestamp = parse_iso8601( - re.sub(r'\.\d+$', '', info['Created'])) + info = self._parse_html5_media_entries( + url, webpage, display_id, m3u8_id='hls', + m3u8_entry_protocol='m3u8_native')[0] + self._sort_formats(info['formats']) - def parse_filename_info(url): - match = re.search(r'/\d+_(?P\d+)x(?P\d+)x(?P\d+)K\.(?P\w+)$', url) - if match: - return { - 'width': int(match.group('width')), - 'height': int(match.group('height')), - 'vbr': int(match.group('bitrate')), - 'ext': match.group('ext') - } - match = re.search(r'/\d+_(?P\d+)K\.(?P\w+)$', url) - if match: - return { - 'vbr': int(match.group('bitrate')), - 'ext': match.group(2) - } - return {} + asset = self._parse_json( + self._search_regex( + r'(?s)currentAsset\s*=\s*({.+?})\s*]+>\s*

%s:

\s*\s*]+>\s*

([^<]+)

' % field, + webpage, field, default=None) - description = '%s\n%s\n%s\n' % ( - info['Description'], info['Actors'], info['Colophon']) - - self._sort_formats(formats) - - display_id = re.sub(r'[^\w\d-]', '', re.sub(r' ', '-', title.lower())) + '-' + asset_id - display_id = re.sub(r'-+', '-', display_id) - - return { - 'id': asset_id, + info.update({ + 'id': asset.get('AssetId') or video_id, 'display_id': display_id, 'title': title, - 'formats': formats, - 'description': description, - 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, - } + 'description': extract('Programinfo'), + 'duration': parse_duration(extract('Tid')), + 'thumbnail': asset.get('AssetImageUrl'), + }) + return info