Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-22 16:44:32 +01:00
Code Issues Releases Wiki Activity

reshet: new CDN

Browse Source
This commit is contained in:
Itay Perl 2020-03-06 13:30:30 +02:00
parent 337a100b93
commit a7effddc0c
1 changed files with 54 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

61
youtube_dl/extractor/reshet.py
View File

@ -4,17 +4,19 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
import os
from ..utils import (
js_to_json,
urljoin,
)
class ReshetIE(InfoExtractor):
_VALID_URL = r'https?://13tv\.co\.il/item/(?P<category>[^/]+)/(?P<series>[^/]+)/(?P<season>[^/]+)/(?P<type>[^/]+)/(?P<id>[^/]+)/?'
_VALID_URL = r'https?://13tv\.co\.il/(?:(?:item/)?[^/]+/[^/]+/[^/]+/[^/]+(?:/(?P<id>[^/]+))?/?|live/?)'
_TEST = {
'url': 'https://13tv.co.il/item/entertainment/gav-hauma/season-10/episodes/jz1a1-1028855',
'note': 'Test brightcove URL extraction',
'note': 'Test URL extraction',
'info_dict': {
'id': '6015811232001',
'ext': 'mp4',
@ -26,17 +28,60 @@ class ReshetIE(InfoExtractor):
}
def _real_extract(self, url):
if re.search('live/?$', url):
reshet_id = 'live'
else:
reshet_id = self._match_id(url)
page = self._download_webpage(url, reshet_id)
data = self._parse_json(re.search(r'var initial_data = (.*?);\n', page).group(1), reshet_id)
item = data['items'][str(data['curItem'])]
brightcove_id = item['video']['videoID']
data = self._parse_json(re.search(r'window.data_query = (.*?).data_query;\n', page).group(1), reshet_id)
liveId = data.get('header', {}).get('Live', {}).get('videoId')
curItem = data.get('curItem')
if liveId is None and curItem is None:
# create a playlist result
entries = []
for item in data['items'].values():
if item.get('video') is None:
continue
entries.append(self.url_result(item['link'],
video_id=item['post_ID'],
video_title=item['title']))
return self.playlist_result(entries)
main_js_url = urljoin(url, re.search(r'<script type="text/javascript" src="(/[^"]*/main.[a-f0-9]+\.js)">', page).group(1))
js = self._download_webpage(main_js_url, reshet_id)
acctId, playerId = re.search('accountID:[^,]*"([0-9]+)",playerID:[^,]*"([^"]+)",', js).groups()
brightcove_url = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s' % (acctId, playerId, brightcove_id)
ccid = re.search('"data-ccid":"(.*?)"', js).group(1)
return self.url_result(brightcove_url, 'BrightcoveNew')
if curItem is not None:
item = data['items'][str(data['curItem'])]
ref = item['video']['videoRef']
video_info = self._download_json('https://13tv-api.oplayer.io/api/getlink/getVideoByFileName?userId=%s&videoName=%s&serverType=web' % (ccid, ref), ref)
v = video_info[0]
base_name, ext = os.path.splitext(v['MediaFile'])
cdn_url = ''.join((v['ProtocolType'], v['ServerAddress'], v['MediaRoot'], base_name, v['Bitrates'], ext, v['StreamingType'], v['Token']))
return {
'id': str(item['video']['videoID']),
'title': ref,
'formats': self._extract_m3u8_formats(cdn_url, ref, 'mp4')
}
elif liveId is not None:
liveName = liveId.split(':')[1]
config_js = self._download_webpage('https://13tv.co.il/wp-content/themes/reshet_tv/build/config.min.js', reshet_id)
config = self._parse_json(js_to_json(re.fullmatch('.*?=(.*);', config_js).group(1)), reshet_id)
channel = config['liveRefId'][liveName]['ch']
video_info = self._download_json('https://13tv-api.oplayer.io/api/getlink/?userId=%s&serverType=web&ch=%s&cdnName=casttime' % (ccid, channel), reshet_id)
video_url = video_info[0]['Link']
return {
'id': str(channel),
'title': liveName,
'formats': self._extract_m3u8_formats(video_url, liveName, 'mp4')
}