_ Git - youtube-dl/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 )
  11
  12
  13 class AolIE(InfoExtractor):
  14     IE_NAME = 'on.aol.com'
  15     _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/video/.*-)(?P<id>[^/?-]+)'
  16
  17     _TESTS = [{
  18         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
  19         'md5': '18ef68f48740e86ae94b98da815eec42',
  20         'info_dict': {
  21             'id': '518167793',
  22             'ext': 'mp4',
  23             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
  24             '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.',
  25             'timestamp': 1395405060,
  26             'upload_date': '20140321',
  27             'uploader': 'Newsy Studio',
  28         },
  29         'params': {
  30             # m3u8 download
  31             'skip_download': True,
  32         }
  33     }, {
  34         'url': 'http://on.aol.com/video/netflix-is-raising-rates-5707d6b8e4b090497b04f706?context=PC:homepage:PL1944:1460189336183',
  35         'info_dict': {
  36             'id': '5707d6b8e4b090497b04f706',
  37             'ext': 'mp4',
  38             'title': 'Netflix is Raising Rates',
  39             'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
  40             'upload_date': '20160408',
  41             'timestamp': 1460123280,
  42             'uploader': 'Veuer',
  43         },
  44         'params': {
  45             # m3u8 download
  46             'skip_download': True,
  47         }
  48     }]
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52
  53         response = self._download_json(
  54             'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
  55             video_id)['response']
  56         if response['statusText'] != 'Ok':
  57             raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
  58
  59         video_data = response['data']
  60         formats = []
  61         m3u8_url = video_data.get('videoMasterPlaylist')
  62         if m3u8_url:
  63             formats.extend(self._extract_m3u8_formats(
  64                 m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  65         for rendition in video_data.get('renditions', []):
  66             video_url = rendition.get('url')
  67             if not video_url:
  68                 continue
  69             ext = rendition.get('format')
  70             if ext == 'm3u8':
  71                 formats.extend(self._extract_m3u8_formats(
  72                     video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  73             else:
  74                 f = {
  75                     'url': video_url,
  76                     'format_id': rendition.get('quality'),
  77                 }
  78                 mobj = re.search(r'(\d+)x(\d+)', video_url)
  79                 if mobj:
  80                     f.update({
  81                         'width': int(mobj.group(1)),
  82                         'height': int(mobj.group(2)),
  83                     })
  84                 formats.append(f)
  85         self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
  86
  87         return {
  88             'id': video_id,
  89             'title': video_data['title'],
  90             'duration': int_or_none(video_data.get('duration')),
  91             'timestamp': int_or_none(video_data.get('publishDate')),
  92             'view_count': int_or_none(video_data.get('views')),
  93             'description': video_data.get('description'),
  94             'uploader': video_data.get('videoOwner'),
  95             'formats': formats,
  96         }
  97
  98
  99 class AolFeaturesIE(InfoExtractor):
 100     IE_NAME = 'features.aol.com'
 101     _VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
 102
 103     _TESTS = [{
 104         'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
 105         'md5': '7db483bb0c09c85e241f84a34238cc75',
 106         'info_dict': {
 107             'id': '519507715',
 108             'ext': 'mp4',
 109             'title': 'What To Watch - February 17, 2016',
 110         },
 111         'add_ie': ['FiveMin'],
 112     }]
 113
 114     def _real_extract(self, url):
 115         display_id = self._match_id(url)
 116         webpage = self._download_webpage(url, display_id)
 117         return self.url_result(self._search_regex(
 118             r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
 119             webpage, '5min embed url'), 'FiveMin')