[shahid] Improve and simplify

This commit is contained in:
Sergey M․ 2015-08-15 18:13:37 +06:00
parent 11bed5827d
commit c576ef1e7c

View File

@ -2,90 +2,106 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..utils import ( from ..utils import (
js_to_json,
ExtractorError, ExtractorError,
int_or_none int_or_none,
parse_iso8601,
) )
class ShahidIE(InfoExtractor): class ShahidIE(InfoExtractor):
_VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?' _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P<id>\d+)/?'
_TESTS = [ _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',
'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': {
'info_dict': { 'id': '90574',
'id': '90574', 'ext': 'm3u8',
'ext': 'm3u8', 'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3',
'title': 'الملك عبدالله الإنسان الموسم 1 كليب 3', 'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان',
'description': 'الفيلم الوثائقي - الملك عبد الله الإنسان', 'duration': 2972,
'duration': 2972, 'timestamp': 1422057420,
}, 'upload_date': '20150123',
'params': {
# m3u8 download
'skip_download': True,
}
}, },
{ 'params': {
# shahid plus subscriber only # m3u8 download
'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', 'skip_download': True,
'only_matching': True
} }
] }, {
# 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
}]
_api_vars = { def _handle_error(self, response):
'type': 'player', if not isinstance(response, dict):
'url': 'http://api.shahid.net/api/v1_1', return
'playerType': 'episode', 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
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)
player_info = '' api_vars = {
flash_vars = self._search_regex('var flashvars = ({[^}]+})', webpage, 'flashvars', None) 'id': video_id,
if flash_vars is not None: 'type': 'player',
for line in flash_vars.splitlines(): 'url': 'http://api.shahid.net/api/v1_1',
if '+' not in line and '(' not in line and ')' not in line: 'playerType': 'episode',
player_info += line }
player_info = self._parse_json(player_info, video_id, js_to_json, False)
if player_info is not None:
for key in self._api_vars:
if key in player_info:
self._api_vars[key] = player_info[key]
player_json_data = self._download_json( flashvars = self._search_regex(
'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-' + video_id + '.type-' + self._api_vars['type'] + '.html', r'var\s+flashvars\s*=\s*({[^}]+})', webpage, 'flashvars', default=None)
video_id if flashvars:
)['data'] for key in api_vars.keys():
if 'url' in player_json_data: value = self._search_regex(
m3u8_url = player_json_data['url'] r'\b%s\s*:\s*(?P<q>["\'])(?P<value>.+?)(?P=q)' % key,
else: flashvars, 'type', default=None, group='value')
for error in player_json_data['error'].values(): if value:
raise ExtractorError(error) api_vars[key] = value
formats = self._extract_m3u8_formats(m3u8_url, video_id)
video_info = self._download_json( player = self._download_json(
self._api_vars['url'] + '/' + self._api_vars['playerType'] + '/' + video_id + '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D', 'https://shahid.mbc.net/arContent/getPlayerContent-param-.id-%s.type-%s.html'
video_id % (video_id, api_vars['type']), video_id, 'Downloading player JSON')
)['data']
if video_info.get('error'): formats = self._extract_m3u8_formats(player['url'], video_id, 'mp4')
for error in video_info['error']:
raise ExtractorError(error) video = self._download_json(
video_info = video_info[self._api_vars['playerType']] '%s/%s/%s?%s' % (
title = video_info['title'] api_vars['url'], api_vars['playerType'], api_vars['id'],
thumbnail = video_info.get('thumbnailUrl') compat_urllib_parse.urlencode({
categories = [category['name'] for category in video_info.get('genres')] 'apiKey': 'sh@hid0nlin3',
description = video_info.get('description') 'hash': 'b2wMCTHpSmyxGqQjJFOycRmLSex+BpTK/ooxy6vHaqs=',
duration = int_or_none(video_info.get('duration')) }).encode('utf-8')),
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]
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'thumbnail': thumbnail,
'categories': categories,
'description': description, 'description': description,
'thumbnail': thumbnail,
'duration': duration, 'duration': duration,
'timestamp': timestamp,
'categories': categories,
'formats': formats, 'formats': formats,
} }