X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/415fdb62500dca2e22067a05008dfbf87c75b662..7df4343e553a9942a290e5e1dffe931261ab844e:/youtube_dl/extractor/aftonbladet.py diff --git a/youtube_dl/extractor/aftonbladet.py b/youtube_dl/extractor/aftonbladet.py index cfc7370..a117502 100644 --- a/youtube_dl/extractor/aftonbladet.py +++ b/youtube_dl/extractor/aftonbladet.py @@ -1,13 +1,12 @@ # encoding: utf-8 from __future__ import unicode_literals -import re - from .common import InfoExtractor +from ..utils import int_or_none class AftonbladetIE(InfoExtractor): - _VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?Particle[0-9]+)\.ab(?:$|[?#])' + _VALID_URL = r'http://tv\.aftonbladet\.se/webbtv.+?(?Particle[0-9]+)\.ab(?:$|[?#])' _TEST = { 'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab', 'info_dict': { @@ -21,9 +20,7 @@ class AftonbladetIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.search(self._VALID_URL, url) - - video_id = mobj.group('video_id') + video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) # find internal video meta data @@ -47,9 +44,9 @@ class AftonbladetIE(InfoExtractor): formats.append({ 'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']), 'ext': 'mp4', - 'width': fmt['width'], - 'height': fmt['height'], - 'tbr': fmt['bitrate'], + 'width': int_or_none(fmt.get('width')), + 'height': int_or_none(fmt.get('height')), + 'tbr': int_or_none(fmt.get('bitrate')), 'protocol': 'http', }) self._sort_formats(formats) @@ -58,9 +55,9 @@ class AftonbladetIE(InfoExtractor): 'id': video_id, 'title': internal_meta_json['title'], 'formats': formats, - 'thumbnail': internal_meta_json['imageUrl'], - 'description': internal_meta_json['shortPreamble'], - 'timestamp': internal_meta_json['timePublished'], - 'duration': internal_meta_json['duration'], - 'view_count': internal_meta_json['views'], + 'thumbnail': internal_meta_json.get('imageUrl'), + 'description': internal_meta_json.get('shortPreamble'), + 'timestamp': int_or_none(internal_meta_json.get('timePublished')), + 'duration': int_or_none(internal_meta_json.get('duration')), + 'view_count': int_or_none(internal_meta_json.get('views')), }