ytdl/youtube_dl/extractor/shahid.py

112 lines
4.0 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2015-07-18 23:10:57 +02:00
from .common import InfoExtractor
from ..compat import compat_urllib_parse_urlencode
from ..utils import (
ExtractorError,
2015-08-15 14:13:37 +02:00
int_or_none,
parse_iso8601,
2015-07-19 00:10:20 +02:00
)
2015-07-18 23:10:57 +02:00
2015-07-18 23:10:57 +02:00
class ShahidIE(InfoExtractor):
_VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
2015-08-15 14:13:37 +02:00
_TESTS = [{
'url': 'https://shahid.mbc.net/ar/episode/90574/%D8%A7%D9%84%D9%85%D9%84%D9%83-%D8%B9%D8%A8%D8%AF%D8%A7%D9%84%D9%84%D9%87-%D8%A7%D9%84%D8%A5%D9%86%D8%B3%D8%A7%D9%86-%D8%A7%D9%84%D9%85%D9%88%D8%B3%D9%85-1-%D9%83%D9%84%D9%8A%D8%A8-3.html',
'info_dict': {
'id': '90574',
2015-09-18 23:10:36 +02:00
'ext': 'mp4',
2015-08-15 14:13:37 +02:00
'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
'duration': 2972,
'timestamp': 1422057420,
'upload_date': '20150123',
2015-07-18 23:10:57 +02:00
},
2015-08-15 14:13:37 +02:00
'params': {
# m3u8 download
'skip_download': True,
2015-07-18 23:10:57 +02:00
}
2015-08-15 14:13:37 +02:00
}, {
# shahid plus subscriber only
'url': 'https://shahid.mbc.net/ar/episode/90511/%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.html',
'only_matching': True
}]
2015-07-18 23:10:57 +02:00
2015-08-15 14:13:37 +02:00
def _handle_error(self, response):
if not isinstance(response, dict):
return
error = response.get('error')
if error:
raise ExtractorError(
'%s returned error: %s' % (self.IE_NAME, '\n'.join(error.values())),
expected=True)
def _download_json(self, url, video_id, note='Downloading JSON metadata'):
response = super(ShahidIE, self)._download_json(url, video_id, note)['data']
self._handle_error(response)
return response
2015-07-18 23:10:57 +02:00
def _real_extract(self, url):
video_id = self._match_id(url)
2015-08-15 14:13:37 +02:00
2015-07-18 23:10:57 +02:00
webpage = self._download_webpage(url, video_id)
2015-08-15 14:13:37 +02:00
api_vars = {
'id': video_id,
'type': 'player',
'url': 'http://api.shahid.net/api/v1_1',
'playerType': 'episode',
}
flashvars = self._search_regex(
r'var\s+flashvars\s*=\s*({[^}]+})', webpage, 'flashvars', default=None)
if flashvars:
for key in api_vars.keys():
value = self._search_regex(
r'\b%s\s*:\s*(?P<q>["\'])(?P<value>.+?)(?P=q)' % key,
flashvars, 'type', default=None, group='value')
if value:
api_vars[key] = value
player = self._download_json(
'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-%s.html'
% (video_id, api_vars['type']), video_id, 'Downloading player JSON')
2015-07-25 19:13:44 +02:00
if player.get('drm'):
raise ExtractorError('This video is DRM protected.', expected=True)
2015-08-15 14:13:37 +02:00
formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
self._sort_formats(formats)
2015-08-15 14:13:37 +02:00
video = self._download_json(
'%s/%s/%s?%s' % (
api_vars['url'], api_vars['playerType'], api_vars['id'],
compat_urllib_parse_urlencode({
2015-08-15 14:13:37 +02:00
'apiKey': 'sh@hid0nlin3',
'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
2015-09-18 23:09:33 +02:00
})),
2015-08-15 14:13:37 +02:00
video_id, 'Downloading video JSON')
video = video[api_vars['playerType']]
title = video['title']
description = video.get('description')
thumbnail = video.get('thumbnailUrl')
duration = int_or_none(video.get('duration'))
timestamp = parse_iso8601(video.get('referenceDate'))
categories = [
category['name']
for category in video.get('genres', []) if 'name' in category]
2015-07-25 19:13:44 +02:00
2015-07-18 23:10:57 +02:00
return {
'id': video_id,
'title': title,
'description': description,
2015-08-15 14:13:37 +02:00
'thumbnail': thumbnail,
2015-07-25 19:13:44 +02:00
'duration': duration,
2015-08-15 14:13:37 +02:00
'timestamp': timestamp,
'categories': categories,
2015-07-18 23:10:57 +02:00
'formats': formats,
}