youtube-dl/youtube_dl/extractor/shahid.py

82 lines
3.2 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2015-07-18 21:10:57 +00:00
from .common import InfoExtractor
from ..utils import (
2015-07-25 17:13:44 +00:00
js_to_json,
ExtractorError,
2015-07-25 17:13:44 +00:00
int_or_none
2015-07-18 22:10:20 +00:00
)
2015-07-18 21:10:57 +00:00
2015-07-18 21:10:57 +00:00
class ShahidIE(InfoExtractor):
_VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
_TESTS = [
{
2015-08-07 20:38:50 +00:00
'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',
2015-07-18 21:10:57 +00:00
'info_dict': {
2015-08-07 20:38:50 +00:00
'id': '90574',
2015-07-18 21:10:57 +00:00
'ext': 'm3u8',
2015-08-07 20:38:50 +00:00
'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
'duration': 2972,
2015-07-18 21:10:57 +00:00
},
'params': {
# m3u8 download
'skip_download': True,
}
},
{
# shahid plus subscriber only
2015-08-07 20:38:50 +00:00
'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',
2015-07-18 21:10:57 +00:00
'only_matching': True
}
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2015-07-25 17:13:44 +00:00
player_info = ''
for line in self._search_regex('var flashvars = ({[^}]+})', webpage, 'flashvars').splitlines():
2015-07-25 17:13:44 +00:00
if '+' not in line and '(' not in line and ')' not in line:
player_info += line
player_info = self._parse_json(js_to_json(player_info), video_id)
video_id = player_info['id']
player_type = player_info['playerType']
player_json_data = self._download_json(
'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-' + video_id + '.type-' + player_info['type'] + '.html',
video_id
)['data']
if 'url' in player_json_data:
m3u8_url = player_json_data['url']
else:
for error in player_json_data['error'].values():
raise ExtractorError(error)
formats = self._extract_m3u8_formats(m3u8_url, video_id)
2015-07-25 17:13:44 +00:00
video_info = self._download_json(
player_info['url'] + '/' + player_type + '/' + video_id + '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D',
2015-07-18 21:10:57 +00:00
video_id
2015-07-25 17:13:44 +00:00
)['data']
if video_info.get('error'):
2015-07-25 17:13:44 +00:00
for error in video_info['error']:
raise ExtractorError(error)
video_info = video_info[player_type]
title = video_info['title']
thumbnail = video_info.get('thumbnailUrl')
categories = [category['name'] for category in video_info.get('genres')]
description = video_info.get('description')
duration = int_or_none(video_info.get('duration'))
2015-07-18 21:10:57 +00:00
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'categories': categories,
'description': description,
2015-07-25 17:13:44 +00:00
'duration': duration,
2015-07-18 21:10:57 +00:00
'formats': formats,
}