Raphaël G. Git Repositories - youtubedl/blob - 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 ..compat import compat_str
   8 from ..utils import (
   9     dict_get,
  10     int_or_none,
  11     try_get,
  12 )
  13
  14
  15 class ABCOTVSIE(InfoExtractor):
  16     IE_NAME = 'abcotvs'
  17     IE_DESC = 'ABC Owned Television Stations'
  18     _VALID_URL = r'https?://(?P<site>abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:(?:/[^/]+)*/(?P<display_id>[^/]+))?/(?P<id>\d+)'
  19     _TESTS = [
  20         {
  21             'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
  22             'info_dict': {
  23                 'id': '472548',
  24                 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
  25                 'ext': 'mp4',
  26                 'title': 'East Bay museum celebrates synthesized music',
  27                 'description': 'md5:24ed2bd527096ec2a5c67b9d5a9005f3',
  28                 'thumbnail': r're:^https?://.*\.jpg$',
  29                 'timestamp': 1421118520,
  30                 'upload_date': '20150113',
  31             },
  32             'params': {
  33                 # m3u8 download
  34                 'skip_download': True,
  35             },
  36         },
  37         {
  38             'url': 'http://abc7news.com/472581',
  39             'only_matching': True,
  40         },
  41         {
  42             'url': 'https://6abc.com/man-75-killed-after-being-struck-by-vehicle-in-chester/5725182/',
  43             'only_matching': True,
  44         },
  45     ]
  46     _SITE_MAP = {
  47         '6abc': 'wpvi',
  48         'abc11': 'wtvd',
  49         'abc13': 'ktrk',
  50         'abc30': 'kfsn',
  51         'abc7': 'kabc',
  52         'abc7chicago': 'wls',
  53         'abc7news': 'kgo',
  54         'abc7ny': 'wabc',
  55     }
  56
  57     def _real_extract(self, url):
  58         site, display_id, video_id = re.match(self._VALID_URL, url).groups()
  59         display_id = display_id or video_id
  60         station = self._SITE_MAP[site]
  61
  62         data = self._download_json(
  63             'https://api.abcotvs.com/v2/content', display_id, query={
  64                 'id': video_id,
  65                 'key': 'otv.web.%s.story' % station,
  66                 'station': station,
  67             })['data']
  68         video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data
  69         video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id))
  70         title = video.get('title') or video['linkText']
  71
  72         formats = []
  73         m3u8_url = video.get('m3u8')
  74         if m3u8_url:
  75             formats = self._extract_m3u8_formats(
  76                 video['m3u8'].split('?')[0], display_id, 'mp4', m3u8_id='hls', fatal=False)
  77         mp4_url = video.get('mp4')
  78         if mp4_url:
  79             formats.append({
  80                 'abr': 128,
  81                 'format_id': 'https',
  82                 'height': 360,
  83                 'url': mp4_url,
  84                 'width': 640,
  85             })
  86         self._sort_formats(formats)
  87
  88         image = video.get('image') or {}
  89
  90         return {
  91             'id': video_id,
  92             'display_id': display_id,
  93             'title': title,
  94             'description': dict_get(video, ('description', 'caption'), try_get(video, lambda x: x['meta']['description'])),
  95             'thumbnail': dict_get(image, ('source', 'dynamicSource')),
  96             'timestamp': int_or_none(video.get('date')),
  97             'duration': int_or_none(video.get('length')),
  98             'formats': formats,
  99         }
 100
 101
 102 class ABCOTVSClipsIE(InfoExtractor):
 103     IE_NAME = 'abcotvs:clips'
 104     _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
 105     _TEST = {
 106         'url': 'https://clips.abcotvs.com/kabc/video/214814',
 107         'info_dict': {
 108             'id': '214814',
 109             'ext': 'mp4',
 110             'title': 'SpaceX launch pad explosion destroys rocket, satellite',
 111             'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
 112             'upload_date': '20160901',
 113             'timestamp': 1472756695,
 114         },
 115         'params': {
 116             # m3u8 download
 117             'skip_download': True,
 118         },
 119     }
 120
 121     def _real_extract(self, url):
 122         video_id = self._match_id(url)
 123         video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
 124         title = video_data['title']
 125         formats = self._extract_m3u8_formats(
 126             video_data['videoURL'].split('?')[0], video_id, 'mp4')
 127         self._sort_formats(formats)
 128
 129         return {
 130             'id': video_id,
 131             'title': title,
 132             'description': video_data.get('description'),
 133             'thumbnail': video_data.get('thumbnailURL'),
 134             'duration': int_or_none(video_data.get('duration')),
 135             'timestamp': int_or_none(video_data.get('pubDate')),
 136             'formats': formats,
 137         }