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 )
  11
  12
  13 class AolIE(InfoExtractor):
  14     IE_NAME = 'on.aol.com'
  15     _VALID_URL = r'(?:aol-video:|https?://on\.aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
  16
  17     _TESTS = [{
  18         # video with 5min ID
  19         'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
  20         'md5': '18ef68f48740e86ae94b98da815eec42',
  21         'info_dict': {
  22             'id': '518167793',
  23             'ext': 'mp4',
  24             'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
  25             '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.',
  26             'timestamp': 1395405060,
  27             'upload_date': '20140321',
  28             'uploader': 'Newsy Studio',
  29         },
  30         'params': {
  31             # m3u8 download
  32             'skip_download': True,
  33         }
  34     }, {
  35         # video with vidible ID
  36         'url': 'http://on.aol.com/video/netflix-is-raising-rates-5707d6b8e4b090497b04f706?context=PC:homepage:PL1944:1460189336183',
  37         'info_dict': {
  38             'id': '5707d6b8e4b090497b04f706',
  39             'ext': 'mp4',
  40             'title': 'Netflix is Raising Rates',
  41             'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
  42             'upload_date': '20160408',
  43             'timestamp': 1460123280,
  44             'uploader': 'Veuer',
  45         },
  46         'params': {
  47             # m3u8 download
  48             'skip_download': True,
  49         }
  50     }, {
  51         'url': 'http://on.aol.com/partners/abc-551438d309eab105804dbfe8/sneak-peek-was-haley-really-framed-570eaebee4b0448640a5c944',
  52         'only_matching': True,
  53     }, {
  54         'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763',
  55         'only_matching': True,
  56     }, {
  57         'url': 'http://on.aol.com/video/519442220',
  58         'only_matching': True,
  59     }, {
  60         'url': 'aol-video:5707d6b8e4b090497b04f706',
  61         'only_matching': True,
  62     }]
  63
  64     def _real_extract(self, url):
  65         video_id = self._match_id(url)
  66
  67         response = self._download_json(
  68             'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
  69             video_id)['response']
  70         if response['statusText'] != 'Ok':
  71             raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
  72
  73         video_data = response['data']
  74         formats = []
  75         m3u8_url = video_data.get('videoMasterPlaylist')
  76         if m3u8_url:
  77             formats.extend(self._extract_m3u8_formats(
  78                 m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  79         for rendition in video_data.get('renditions', []):
  80             video_url = rendition.get('url')
  81             if not video_url:
  82                 continue
  83             ext = rendition.get('format')
  84             if ext == 'm3u8':
  85                 formats.extend(self._extract_m3u8_formats(
  86                     video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
  87             else:
  88                 f = {
  89                     'url': video_url,
  90                     'format_id': rendition.get('quality'),
  91                 }
  92                 mobj = re.search(r'(\d+)x(\d+)', video_url)
  93                 if mobj:
  94                     f.update({
  95                         'width': int(mobj.group(1)),
  96                         'height': int(mobj.group(2)),
  97                     })
  98                 formats.append(f)
  99         self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
 100
 101         return {
 102             'id': video_id,
 103             'title': video_data['title'],
 104             'duration': int_or_none(video_data.get('duration')),
 105             'timestamp': int_or_none(video_data.get('publishDate')),
 106             'view_count': int_or_none(video_data.get('views')),
 107             'description': video_data.get('description'),
 108             'uploader': video_data.get('videoOwner'),
 109             'formats': formats,
 110         }
 111
 112
 113 class AolFeaturesIE(InfoExtractor):
 114     IE_NAME = 'features.aol.com'
 115     _VALID_URL = r'https?://features\.aol\.com/video/(?P<id>[^/?#]+)'
 116
 117     _TESTS = [{
 118         'url': 'http://features.aol.com/video/behind-secret-second-careers-late-night-talk-show-hosts',
 119         'md5': '7db483bb0c09c85e241f84a34238cc75',
 120         'info_dict': {
 121             'id': '519507715',
 122             'ext': 'mp4',
 123             'title': 'What To Watch - February 17, 2016',
 124         },
 125         'add_ie': ['FiveMin'],
 126     }]
 127
 128     def _real_extract(self, url):
 129         display_id = self._match_id(url)
 130         webpage = self._download_webpage(url, display_id)
 131         return self.url_result(self._search_regex(
 132             r'<script type="text/javascript" src="(https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js[^"]+)"',
 133             webpage, '5min embed url'), 'FiveMin')