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 ..utils import (
   8     int_or_none,
   9     parse_iso8601,
  10 )
  11
  12
  13 class ABCOTVSIE(InfoExtractor):
  14     IE_NAME = 'abcotvs'
  15     IE_DESC = 'ABC Owned Television Stations'
  16     _VALID_URL = r'https?://(?:abc(?:7(?:news|ny|chicago)?|11|13|30)|6abc)\.com(?:/[^/]+/(?P<display_id>[^/]+))?/(?P<id>\d+)'
  17     _TESTS = [
  18         {
  19             'url': 'http://abc7news.com/entertainment/east-bay-museum-celebrates-vintage-synthesizers/472581/',
  20             'info_dict': {
  21                 'id': '472581',
  22                 'display_id': 'east-bay-museum-celebrates-vintage-synthesizers',
  23                 'ext': 'mp4',
  24                 'title': 'East Bay museum celebrates vintage synthesizers',
  25                 'description': 'md5:a4f10fb2f2a02565c1749d4adbab4b10',
  26                 'thumbnail': 're:^https?://.*\.jpg$',
  27                 'timestamp': 1421123075,
  28                 'upload_date': '20150113',
  29                 'uploader': 'Jonathan Bloom',
  30             },
  31             'params': {
  32                 # m3u8 download
  33                 'skip_download': True,
  34             },
  35         },
  36         {
  37             'url': 'http://abc7news.com/472581',
  38             'only_matching': True,
  39         },
  40     ]
  41
  42     def _real_extract(self, url):
  43         mobj = re.match(self._VALID_URL, url)
  44         video_id = mobj.group('id')
  45         display_id = mobj.group('display_id') or video_id
  46
  47         webpage = self._download_webpage(url, display_id)
  48
  49         m3u8 = self._html_search_meta(
  50             'contentURL', webpage, 'm3u8 url', fatal=True).split('?')[0]
  51
  52         formats = self._extract_m3u8_formats(m3u8, display_id, 'mp4')
  53         self._sort_formats(formats)
  54
  55         title = self._og_search_title(webpage).strip()
  56         description = self._og_search_description(webpage).strip()
  57         thumbnail = self._og_search_thumbnail(webpage)
  58         timestamp = parse_iso8601(self._search_regex(
  59             r'<div class="meta">\s*<time class="timeago" datetime="([^"]+)">',
  60             webpage, 'upload date', fatal=False))
  61         uploader = self._search_regex(
  62             r'rel="author">([^<]+)</a>',
  63             webpage, 'uploader', default=None)
  64
  65         return {
  66             'id': video_id,
  67             'display_id': display_id,
  68             'title': title,
  69             'description': description,
  70             'thumbnail': thumbnail,
  71             'timestamp': timestamp,
  72             'uploader': uploader,
  73             'formats': formats,
  74         }
  75
  76
  77 class ABCOTVSClipsIE(InfoExtractor):
  78     IE_NAME = 'abcotvs:clips'
  79     _VALID_URL = r'https?://clips\.abcotvs\.com/(?:[^/]+/)*video/(?P<id>\d+)'
  80     _TEST = {
  81         'url': 'https://clips.abcotvs.com/kabc/video/214814',
  82         'info_dict': {
  83             'id': '214814',
  84             'ext': 'mp4',
  85             'title': 'SpaceX launch pad explosion destroys rocket, satellite',
  86             'description': 'md5:9f186e5ad8f490f65409965ee9c7be1b',
  87             'upload_date': '20160901',
  88             'timestamp': 1472756695,
  89         },
  90         'params': {
  91             # m3u8 download
  92             'skip_download': True,
  93         },
  94     }
  95
  96     def _real_extract(self, url):
  97         video_id = self._match_id(url)
  98         video_data = self._download_json('https://clips.abcotvs.com/vogo/video/getByIds?ids=' + video_id, video_id)['results'][0]
  99         title = video_data['title']
 100         formats = self._extract_m3u8_formats(
 101             video_data['videoURL'].split('?')[0], video_id, 'mp4')
 102         self._sort_formats(formats)
 103
 104         return {
 105             'id': video_id,
 106             'title': title,
 107             'description': video_data.get('description'),
 108             'thumbnail': video_data.get('thumbnailURL'),
 109             'duration': int_or_none(video_data.get('duration')),
 110             'timestamp': int_or_none(video_data.get('pubDate')),
 111             'formats': formats,
 112         }