+# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from .fivemin import FiveMinIE
+from ..utils import (
+ ExtractorError,
+ int_or_none,
+)
class AolIE(InfoExtractor):
IE_NAME = 'on.aol.com'
- _VALID_URL = r'''(?x)
- (?:
- aol-video:|
- http://on\.aol\.com/
- (?:
- video/.*-|
- playlist/(?P<playlist_display_id>[^/?#]+?)-(?P<playlist_id>[0-9]+)[?#].*_videoid=
- )
- )
- (?P<id>[0-9]+)
- (?:$|\?)
- '''
+ _VALID_URL = r'(?:aol-video:|https?://(?:(?:www|on)\.)?aol\.com/(?:[^/]+/)*(?:[^/?#&]+-)?)(?P<id>[^/?#&]+)'
_TESTS = [{
+ # video with 5min ID
'url': 'http://on.aol.com/video/u-s--official-warns-of-largest-ever-irs-phone-scam-518167793?icid=OnHomepageC2Wide_MustSee_Img',
'md5': '18ef68f48740e86ae94b98da815eec42',
'info_dict': {
'id': '518167793',
'ext': 'mp4',
'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
+ '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.',
+ 'timestamp': 1395405060,
+ 'upload_date': '20140321',
+ 'uploader': 'Newsy Studio',
},
- 'add_ie': ['FiveMin'],
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ }
}, {
- 'url': 'http://on.aol.com/playlist/brace-yourself---todays-weirdest-news-152147?icid=OnHomepageC4_Omg_Img#_videoid=518184316',
+ # video with vidible ID
+ 'url': 'http://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
'info_dict': {
- 'id': '152147',
- 'title': 'Brace Yourself - Today\'s Weirdest News',
+ 'id': '5707d6b8e4b090497b04f706',
+ 'ext': 'mp4',
+ 'title': 'Netflix is Raising Rates',
+ 'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
+ 'upload_date': '20160408',
+ 'timestamp': 1460123280,
+ 'uploader': 'Veuer',
},
- 'playlist_mincount': 10,
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ }
+ }, {
+ 'url': 'http://on.aol.com/partners/abc-551438d309eab105804dbfe8/sneak-peek-was-haley-really-framed-570eaebee4b0448640a5c944',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://on.aol.com/shows/park-bench-shw518173474-559a1b9be4b0c3bfad3357a7?context=SH:SHW518173474:PL4327:1460619712763',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://on.aol.com/video/519442220',
+ 'only_matching': True,
+ }, {
+ 'url': 'aol-video:5707d6b8e4b090497b04f706',
+ 'only_matching': True,
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- playlist_id = mobj.group('playlist_id')
- if playlist_id and not self._downloader.params.get('noplaylist'):
- self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
+ video_id = self._match_id(url)
- webpage = self._download_webpage(url, playlist_id)
- title = self._html_search_regex(
- r'<h1 class="video-title[^"]*">(.+?)</h1>', webpage, 'title')
- playlist_html = self._search_regex(
- r"(?s)<ul\s+class='video-related[^']*'>(.*?)</ul>", webpage,
- 'playlist HTML')
- entries = [{
- '_type': 'url',
- 'url': 'aol-video:%s' % m.group('id'),
- 'ie_key': 'Aol',
- } for m in re.finditer(
- r"<a\s+href='.*videoid=(?P<id>[0-9]+)'\s+class='video-thumb'>",
- playlist_html)]
+ response = self._download_json(
+ 'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
+ video_id)['response']
+ if response['statusText'] != 'Ok':
+ raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
- return {
- '_type': 'playlist',
- 'id': playlist_id,
- 'display_id': mobj.group('playlist_display_id'),
- 'title': title,
- 'entries': entries,
- }
+ video_data = response['data']
+ formats = []
+ m3u8_url = video_data.get('videoMasterPlaylist')
+ if m3u8_url:
+ formats.extend(self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+ for rendition in video_data.get('renditions', []):
+ video_url = rendition.get('url')
+ if not video_url:
+ continue
+ ext = rendition.get('format')
+ if ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+ else:
+ f = {
+ 'url': video_url,
+ 'format_id': rendition.get('quality'),
+ }
+ mobj = re.search(r'(\d+)x(\d+)', video_url)
+ if mobj:
+ f.update({
+ 'width': int(mobj.group(1)),
+ 'height': int(mobj.group(2)),
+ })
+ formats.append(f)
+ self._sort_formats(formats, ('width', 'height', 'tbr', 'format_id'))
- return FiveMinIE._build_result(video_id)
+ return {
+ 'id': video_id,
+ 'title': video_data['title'],
+ 'duration': int_or_none(video_data.get('duration')),
+ 'timestamp': int_or_none(video_data.get('publishDate')),
+ 'view_count': int_or_none(video_data.get('views')),
+ 'description': video_data.get('description'),
+ 'uploader': video_data.get('videoOwner'),
+ 'formats': formats,
+ }
Rapsys Git / youtubedl / blobdiff