gitlab-com-dstftw/youtube-dl
1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
Code Issues Releases Wiki Activity

[shahid] improve info extraction

Browse source
This commit is contained in:
remitamine 2015-07-25 18:13:44 +01:00
parent 3c07a729a6
commit a62fd1af27
1 changed files with 31 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
youtube_dl/extractor/shahid.py
View file

@ -1,7 +1,8 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
get_element_by_id, js_to_json,
ExtractorError, ExtractorError,
int_or_none
) )
class ShahidIE(InfoExtractor): class ShahidIE(InfoExtractor):
@ -12,8 +13,9 @@ class ShahidIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '108084', 'id': '108084',
'ext': 'm3u8', 'ext': 'm3u8',
'title': 'بسم الله', 'title': 'خواطر الموسم 11 الحلقة 1',
'description': 'بسم الله' 'description': 'بسم الله',
'duration': 1166,
}, },
'params': { 'params': {
# m3u8 download # m3u8 download
@ -30,16 +32,33 @@ class ShahidIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
json_data = self._parse_json( player_info = ''
get_element_by_id('jsonld', webpage), for line in self._search_regex( 'var flashvars = ({[^}]+})', webpage, 'flashvars').splitlines():
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']
video_info = self._download_json(
player_info['url'] + '/' + player_type + '/' + video_id +
'?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D',
video_id video_id
) )['data']
title = json_data['name'] if video_info['error']:
thumbnail = json_data.get('image') for error in video_info['error']:
categories = json_data.get('genre') raise ExtractorError(error)
description = json_data.get('description') video_info = video_info[player_type]
if video_info.get('availabilities').get('plus'):
raise ExtractorError('plus members only')
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'))
player_json_data = self._download_json( player_json_data = self._download_json(
'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-'+video_id+'.type-player.html', 'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-' + video_id + '.type-' + player_info['type'] + '.html',
video_id video_id
)['data'] )['data']
if 'url' in player_json_data: if 'url' in player_json_data:
@ -55,5 +74,6 @@ class ShahidIE(InfoExtractor):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'categories': categories, 'categories': categories,
'description': description, 'description': description,
'duration': duration,
'formats': formats, 'formats': formats,
} }