From 3be3c622dc1d3d7b92c5268a079d202a9f2b0a5a Mon Sep 17 00:00:00 2001 From: remitamine Date: Thu, 6 Aug 2015 19:37:45 +0100 Subject: [shahid] generic errors handling and check with flake8 --- youtube_dl/extractor/shahid.py | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) (limited to 'youtube_dl/extractor/shahid.py') diff --git a/youtube_dl/extractor/shahid.py b/youtube_dl/extractor/shahid.py index b3b45da..57c1598 100644 --- a/youtube_dl/extractor/shahid.py +++ b/youtube_dl/extractor/shahid.py @@ -1,3 +1,6 @@ +# coding: utf-8 +from __future__ import unicode_literals + from .common import InfoExtractor from ..utils import ( js_to_json, @@ -5,6 +8,7 @@ from ..utils import ( int_or_none ) + class ShahidIE(InfoExtractor): _VALID_URL = r'https?://shahid\.mbc\.net/ar/episode/(?P\d+)/?' _TESTS = [ @@ -23,7 +27,7 @@ class ShahidIE(InfoExtractor): } }, { - #shahid plus subscriber only + # shahid plus subscriber only 'url': 'https://shahid.mbc.net/ar/series/90497/%D9%85%D8%B1%D8%A7%D9%8A%D8%A7-2011.html', 'only_matching': True } @@ -32,42 +36,40 @@ class ShahidIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) + player_info = '' - for line in self._search_regex( 'var flashvars = ({[^}]+})', webpage, 'flashvars').splitlines(): + 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'] + 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) + video_info = self._download_json( - player_info['url'] + '/' + player_type + '/' + video_id + - '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D', + player_info['url'] + '/' + player_type + '/' + video_id + '?apiKey=sh%40hid0nlin3&hash=b2wMCTHpSmyxGqQjJFOycRmLSex%2BBpTK%2Fooxy6vHaqs%3D', video_id )['data'] - if video_info['error']: + if video_info.get('error'): for error in video_info['error']: raise ExtractorError(error) 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( - '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) - return - formats = self._extract_m3u8_formats(m3u8_url, video_id) return { 'id': video_id, 'title': title, -- cgit v1.1