# coding: utf-8 from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( int_or_none, parse_iso8601, ) class ABCOTVSIE(InfoExtractor): IE_NAME = 'abcotvs' IE_DESC = 'ABC Owned Television Stations' _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P[^/]+))?/(?P\d+)' _TESTS = [ { 'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/', 'info_dict': { 'id': '472581', 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers', 'ext': 'mp4', 'title': 'East Bay museum celebrates vintage synthesizers', 'description': 'md5:24ed2bd527096ec2a5c67b9d5a9005f3', 'thumbnail': r're:^https?://.*\.jpg$', 'timestamp': 1421123075, 'upload_date': '20150113', 'uploader': 'Jonathan Bloom', }, 'params': { # m3u8 download 'skip_download': True, }, }, { 'url': 'http://abc7news.com/472581', 'only_matching': True, }, ] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') display_id = mobj.group('display_id') or video_id webpage = self._download_webpage(url, display_id) m3u8 = self._html_search_meta( 'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0] formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4') self._sort_formats(formats) title = self._og_search_title(webpage).strip() description = self._og_search_description(webpage).strip() thumbnail = self._og_search_thumbnail(webpage) timestamp = parse_iso8601(self._search_regex( r'
\s*