Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/aol.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     ExtractorError,
   9     int_or_none,
  10     url_or_none,
  11 )
  12
  13
  14 class AolIE(InfoExtractor):
  15     IE_NAME = 'on.aol.com'
  16     _VALID_URL = r'(?:aol-video:|https?://(?:(?:www|on)\.)?aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
  17
  18     _TESTS = [{
  19         # video with 5min ID
  20         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
  21         'md5': '18ef68f48740e86ae94b98da815eec42',
  22         'info_dict': {
  23             'id': '518167793',
  24             'ext': 'mp4',
  25             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
  26             'description': 'A major phone scam has cost thousands of taxpayers more than $1 million, with less than a month until income tax returns are due to the IRS.',
  27             'timestamp': 1395405060,
  28             'upload_date': '20140321',
  29             'uploader': 'Newsy Studio',
  30         },
  31         'params': {
  32             # m3u8 download
  33             'skip_download': True,
  34         }
  35     }, {
  36         # video with vidible ID
  37         'url': 'http://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
  38         'info_dict': {
  39             'id': '5707d6b8e4b090497b04f706',
  40             'ext': 'mp4',
  41             'title': 'Netflix is Raising Rates',
  42             'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
  43             'upload_date': '20160408',
  44             'timestamp': 1460123280,
  45             'uploader': 'Veuer',
  46         },
  47         'params': {
  48             # m3u8 download
  49             'skip_download': True,
  50         }
  51     }, {
  52         'url': 'http://on.aol.com/partners/abc-551438d309eab105804dbfe8/sneak-peek-was-haley-really-framed-570eaebee4b0448640a5c944',
  53         'only_matching': True,
  54     }, {
  55         'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763',
  56         'only_matching': True,
  57     }, {
  58         'url': 'http://on.aol.com/video/519442220',
  59         'only_matching': True,
  60     }, {
  61         'url': 'aol-video:5707d6b8e4b090497b04f706',
  62         'only_matching': True,
  63     }]
  64
  65     def _real_extract(self, url):
  66         video_id = self._match_id(url)
  67
  68         response = self._download_json(
  69             'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
  70             video_id)['response']
  71         if response['statusText'] != 'Ok':
  72             raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
  73
  74         video_data = response['data']
  75         formats = []
  76         m3u8_url = video_data.get('videoMasterPlaylist')
  77         if m3u8_url:
  78             formats.extend(self._extract_m3u8_formats(
  79                 m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  80         for rendition in video_data.get('renditions', []):
  81             video_url = url_or_none(rendition.get('url'))
  82             if not video_url:
  83                 continue
  84             ext = rendition.get('format')
  85             if ext == 'm3u8':
  86                 formats.extend(self._extract_m3u8_formats(
  87                     video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  88             else:
  89                 f = {
  90                     'url': video_url,
  91                     'format_id': rendition.get('quality'),
  92                 }
  93                 mobj = re.search(r'(\d+)x(\d+)', video_url)
  94                 if mobj:
  95                     f.update({
  96                         'width': int(mobj.group(1)),
  97                         'height': int(mobj.group(2)),
  98                     })
  99                 formats.append(f)
 100         self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
 101
 102         return {
 103             'id': video_id,
 104             'title': video_data['title'],
 105             'duration': int_or_none(video_data.get('duration')),
 106             'timestamp': int_or_none(video_data.get('publishDate')),
 107             'view_count': int_or_none(video_data.get('views')),
 108             'description': video_data.get('description'),
 109             'uploader': video_data.get('videoOwner'),
 110             'formats': formats,
 111         }