yt-dlp/youtube_dl/extractor/shahid.py

138 lines
5.1 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
import json
2015-07-18 17:10:57 -04:00
from .common import InfoExtractor
from ..compat import compat_HTTPError
from ..utils import (
ExtractorError,
2015-08-15 08:13:37 -04:00
int_or_none,
parse_iso8601,
str_or_none,
urlencode_postdata,
clean_html,
2015-07-18 18:10:20 -04:00
)
2015-07-18 17:10:57 -04:00
2015-07-18 17:10:57 -04:00
class ShahidIE(InfoExtractor):
_NETRC_MACHINE = 'shahid'
2017-10-12 05:20:07 -04:00
_VALID_URL = r'https?://shahid\.mbc\.net/ar/(?:serie|show|movie)s/[^/]+/(?P<type>episode|clip|movie)-(?P<id>\d+)'
2015-08-15 08:13:37 -04:00
_TESTS = [{
2017-10-12 05:20:07 -04:00
'url': 'https://shahid.mbc.net/ar/shows/%D9%85%D8%AC%D9%84%D8%B3-%D8%A7%D9%84%D8%B4%D8%A8%D8%A7%D8%A8-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-1/clip-275286',
2015-08-15 08:13:37 -04:00
'info_dict': {
2017-10-12 05:20:07 -04:00
'id': '275286',
2015-09-18 17:10:36 -04:00
'ext': 'mp4',
2017-10-12 05:20:07 -04:00
'title': 'مجلس الشباب الموسم 1 كليب 1',
'timestamp': 1506988800,
'upload_date': '20171003',
2015-07-18 17:10:57 -04:00
},
2015-08-15 08:13:37 -04:00
'params': {
# m3u8 download
'skip_download': True,
2015-07-18 17:10:57 -04:00
}
}, {
2017-10-12 05:20:07 -04:00
'url': 'https://shahid.mbc.net/ar/movies/%D8%A7%D9%84%D9%82%D9%86%D8%A7%D8%B5%D8%A9/movie-151746',
'only_matching': True
2015-08-15 08:13:37 -04:00
}, {
# shahid plus subscriber only
2017-10-12 05:20:07 -04:00
'url': 'https://shahid.mbc.net/ar/series/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D8%A7%D9%84%D8%AD%D9%84%D9%82%D8%A9-1/episode-90511',
2015-08-15 08:13:37 -04:00
'only_matching': True
}]
2015-07-18 17:10:57 -04:00
2017-10-12 05:20:07 -04:00
def _api2_request(self, *args, **kwargs):
try:
2017-10-12 05:20:07 -04:00
return self._download_json(*args, **kwargs)
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError):
fail_data = self._parse_json(
e.cause.read().decode('utf-8'), None, fatal=False)
if fail_data:
faults = fail_data.get('faults', [])
faults_message = ', '.join([clean_html(fault['userMessage']) for fault in faults if fault.get('userMessage')])
if faults_message:
raise ExtractorError(faults_message, expected=True)
raise
2017-10-12 05:20:07 -04:00
def _real_initialize(self):
email, password = self._get_login_info()
if email is None:
return
user_data = self._api2_request(
'https://shahid.mbc.net/wd/service/users/login',
None, 'Logging in', data=json.dumps({
'email': email,
'password': password,
'basic': 'false',
}).encode('utf-8'), headers={
'Content-Type': 'application/json; charset=UTF-8',
})['user']
self._download_webpage(
'https://shahid.mbc.net/populateContext',
None, 'Populate Context', data=urlencode_postdata({
'firstName': user_data['firstName'],
'lastName': user_data['lastName'],
'userName': user_data['email'],
'csg_user_name': user_data['email'],
'subscriberId': user_data['id'],
'sessionId': user_data['sessionId'],
}))
def _get_api_data(self, response):
data = response.get('data', {})
error = data.get('error')
2015-08-15 08:13:37 -04:00
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
expected=True)
return data
2015-07-18 17:10:57 -04:00
def _real_extract(self, url):
page_type, video_id = re.match(self._VALID_URL, url).groups()
2017-10-12 05:20:07 -04:00
if page_type == 'clip':
page_type = 'episode'
2015-08-15 08:13:37 -04:00
2017-10-12 05:20:07 -04:00
playout = self._api2_request(
'https://api2.shahid.net/proxy/v2/playout/url/' + video_id,
video_id, 'Downloading player JSON')['playout']
2015-07-25 13:13:44 -04:00
2017-10-12 05:20:07 -04:00
if playout.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
2017-10-12 05:20:07 -04:00
formats = self._extract_m3u8_formats(playout['url'], video_id, 'mp4')
self._sort_formats(formats)
video = self._get_api_data(self._download_json(
'http://api.shahid.net/api/v1_1/%s/%s' % (page_type, video_id),
video_id, 'Downloading video JSON', query={
'apiKey': 'sh@hid0nlin3',
'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
}))[page_type]
2015-08-15 08:13:37 -04:00
title = video['title']
categories = [
category['name']
for category in video.get('genres', []) if 'name' in category]
2015-07-25 13:13:44 -04:00
2015-07-18 17:10:57 -04:00
return {
'id': video_id,
'title': title,
'description': video.get('description'),
'thumbnail': video.get('thumbnailUrl'),
'duration': int_or_none(video.get('duration')),
'timestamp': parse_iso8601(video.get('referenceDate')),
2015-08-15 08:13:37 -04:00
'categories': categories,
'series': video.get('showTitle') or video.get('showName'),
'season': video.get('seasonTitle'),
'season_number': int_or_none(video.get('seasonNumber')),
'season_id': str_or_none(video.get('seasonId')),
'episode_number': int_or_none(video.get('number')),
'episode_id': video_id,
2015-07-18 17:10:57 -04:00
'formats': formats,
}