youtube_dl/extractor/abcotvs.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     int_or_none,
   9     parse_iso8601,
  10 )
  11
  12
  13 class ABCOTVSIE(InfoExtractor):
  14     IE_NAME = 'abcotvs'
  15     _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
  16     _TESTS = [
  17         {
  18             'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
  19             'info_dict': {
  20                 'id': '472581',
  21                 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
  22                 'ext': 'mp4',
  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',
  29             },
  30             'params': {
  31                 # m3u8 download
  32                 'skip_download': True,
  33             },
  34         },
  35         {
  36             'url': 'http://abc7news.com/472581',
  37             'only_matching': True,
  38         },
  39     ]
  40
  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
  45
  46         webpage = self._download_webpage(url, display_id)
  47
  48         m3u8 = self._html_search_meta(
  49             'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
  50
  51         formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
  52         self._sort_formats(formats)
  53
  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)
  63
  64         return {
  65             'id': video_id,
  66             'display_id': display_id,
  67             'title': title,
  68             'description': description,
  69             'thumbnail': thumbnail,
  70             'timestamp': timestamp,
  71             'uploader': uploader,
  72             'formats': formats,
  73         }
  74
  75
  76 class ABCOTVSClipsIE(InfoExtractor):
  77     IE_NAME = 'abcotvs:clips'
  78     _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
  79     _TEST = {
  80         'url': 'https://clips.abcotvs.com/kabc/video/214814',
  81         'info_dict': {
  82             'id': '214814',
  83             'ext': 'mp4',
  84             'title': 'SpaceX launch pad explosion destroys rocket, satellite',
  85             'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
  86             'upload_date': '20160901',
  87             'timestamp': 1472756695,
  88         },
  89         'params': {
  90             # m3u8 download
  91             'skip_download': True,
  92         },
  93     }
  94
  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)
 102
 103         return {
 104             'id': video_id,
 105             'title': title,
 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')),
 110             'formats': formats,
 111         }