From 856150d05647904a5cf6c519c6e276ce3536bd20 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sat, 11 Jun 2016 18:22:26 +0800 Subject: [PATCH] [telewebion] Add new extractor (closes #5135) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/telewebion.py | 55 ++++++++++++++++++++++++++++++ 2 files changed, 56 insertions(+) create mode 100644 youtube_dl/extractor/telewebion.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 38708294a..36ddc1f73 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -777,6 +777,7 @@ from .telegraaf import TelegraafIE from .telemb import TeleMBIE from .teletask import TeleTaskIE +from .telewebion import TelewebionIE from .testurl import TestURLIE from .tf1 import TF1IE from .theintercept import TheInterceptIE diff --git a/youtube_dl/extractor/telewebion.py b/youtube_dl/extractor/telewebion.py new file mode 100644 index 000000000..77916c601 --- /dev/null +++ b/youtube_dl/extractor/telewebion.py @@ -0,0 +1,55 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor + + +class TelewebionIE(InfoExtractor): + _VALID_URL = r'https?://www\.telewebion\.com/#!/episode/(?P\d+)' + + _TEST = { + 'url': 'http://www.telewebion.com/#!/episode/1263668/', + 'info_dict': { + 'id': '1263668', + 'ext': 'mp4', + 'title': 'قرعه\u200cکشی لیگ قهرمانان اروپا', + 'thumbnail': 're:^https?://.*\.jpg', + 'view_count': int, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + } + + def _real_extract(self, url): + video_id = self._match_id(url) + + secure_token = self._download_webpage( + 'http://m.s2.telewebion.com/op/op?action=getSecurityToken', video_id) + episode_details = self._download_json( + 'http://m.s2.telewebion.com/op/op', video_id, + query={'action': 'getEpisodeDetails', 'episode_id': video_id}) + + m3u8_url = 'http://m.s1.telewebion.com/smil/%s.m3u8?filepath=%s&m3u8=1&secure_token=%s' % ( + video_id, episode_details['file_path'], secure_token) + formats = self._extract_m3u8_formats( + m3u8_url, video_id, ext='mp4', m3u8_id='hls') + + picture_paths = [ + episode_details.get('picture_path'), + episode_details.get('large_picture_path'), + ] + + thumbnails = [{ + 'url': picture_path, + 'preference': idx, + } for idx, picture_path in enumerate(picture_paths) if picture_path is not None] + + return { + 'id': video_id, + 'title': episode_details['title'], + 'formats': formats, + 'thumbnails': thumbnails, + 'view_count': episode_details.get('view_count'), + }