2 from __future__ import unicode_literals
6 from .common import InfoExtractor
13 class ABCOTVSIE(InfoExtractor):
15 _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
18 'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
21 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
23 'title': 'East Bay museum celebrates vintage synthesizers',
24 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
25 'thumbnail': 're:^https?://.*\.jpg$',
26 'timestamp': 1421123075,
27 'upload_date': '20150113',
28 'uploader': 'Jonathan Bloom',
32 'skip_download': True,
36 'url': 'http://abc7news.com/472581',
37 'only_matching': True,
41 def _real_extract(self, url):
42 mobj = re.match(self._VALID_URL, url)
43 video_id = mobj.group('id')
44 display_id = mobj.group('display_id') or video_id
46 webpage = self._download_webpage(url, display_id)
48 m3u8 = self._html_search_meta(
49 'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
51 formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
52 self._sort_formats(formats)
54 title = self._og_search_title(webpage).strip()
55 description = self._og_search_description(webpage).strip()
56 thumbnail = self._og_search_thumbnail(webpage)
57 timestamp = parse_iso8601(self._search_regex(
58 r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
59 webpage, 'upload date', fatal=False))
60 uploader = self._search_regex(
61 r'rel="author">([^<]+)</a>',
62 webpage, 'uploader', default=None)
66 'display_id': display_id,
68 'description': description,
69 'thumbnail': thumbnail,
70 'timestamp': timestamp,
76 class ABCOTVSClipsIE(InfoExtractor):
77 IE_NAME = 'abcotvs:clips'
78 _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
80 'url': 'https://clips.abcotvs.com/kabc/video/214814',
84 'title': 'SpaceX launch pad explosion destroys rocket, satellite',
85 'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
86 'upload_date': '20160901',
87 'timestamp': 1472756695,
91 'skip_download': True,
95 def _real_extract(self, url):
96 video_id = self._match_id(url)
97 video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
98 title = video_data['title']
99 formats = self._extract_m3u8_formats(
100 video_data['videoURL'].split('?')[0], video_id, 'mp4')
101 self._sort_formats(formats)
106 'description': video_data.get('description'),
107 'thumbnail': video_data.get('thumbnailURL'),
108 'duration': int_or_none(video_data.get('duration')),
109 'timestamp': int_or_none(video_data.get('pubDate')),