From 447a5a710dcd05741ea8cefa2fe98b333534e07d Mon Sep 17 00:00:00 2001 From: sprhawk <465558+sprhawk@users.noreply.github.com> Date: Tue, 26 Dec 2017 16:18:35 +0800 Subject: [PATCH] added weibo mobile site support --- youtube_dl/extractor/extractors.py | 5 +++- youtube_dl/extractor/weibo.py | 46 ++++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 12dc2e7e8..f1ea735b5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1286,7 +1286,10 @@ WebOfStoriesIE, WebOfStoriesPlaylistIE, ) -from .weibo import WeiboIE +from .weibo import ( + WeiboIE, + WeiboMobileIE +) from .weiqitv import WeiqiTVIE from .wimp import WimpIE from .wistia import WistiaIE diff --git a/youtube_dl/extractor/weibo.py b/youtube_dl/extractor/weibo.py index b835f8975..eda0fa63d 100644 --- a/youtube_dl/extractor/weibo.py +++ b/youtube_dl/extractor/weibo.py @@ -9,6 +9,11 @@ import json import random as rnd from os import path +import re + +from ..utils import ( + js_to_json, +) class WeiboIE(InfoExtractor): _VALID_URL = r'https?://weibo\.com/[0-9]+/(?P[a-zA-Z0-9]+)' @@ -103,3 +108,44 @@ def _real_extract(self, url): 'formats': formats # TODO more properties (see youtube_dl/extractor/common.py) } + +class WeiboMobileIE(InfoExtractor): + _VALID_URL = r'https?://m.weibo.cn/status/(?P[0-9]+)(\?.+)?' + _TEST = { + 'url': 'https://m.weibo.cn/status/4189191225395228?wm=3333_2001&sourcetype=weixin&featurecode=newtitle&from=singlemessage&isappinstalled=0', + 'info_dict': { + 'id': '4189191225395228', + 'ext': 'mp4', + 'title': '午睡当然是要甜甜蜜蜜的啦', + 'uploader': '柴犬柴犬' + } + } + + def _real_extract(self, url): + video_id = self._match_id(url) + headers = { + 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8', + 'Accept-Encoding': 'gzip, deflate, br', + 'Accept-Language': 'en,zh-CN;q=0.9,zh;q=0.8', + 'Upgrade-Insecure-Requests': '1', + } + # to get Referer url for genvisitor + webpage,urlh = self._download_webpage_handle(url, video_id, headers=headers, note="visit the page") + js_code = self._search_regex(r'var\s+\$render_data\s*=\s*\[({.*})\]\[0\] \|\| {};', webpage, 'js_code', flags = re.DOTALL) + weibo_info = self._parse_json(js_code, video_id, transform_source=js_to_json) + page_info = weibo_info['status']['page_info'] + title = weibo_info['status']['status_title'] + format = { + 'url': page_info['media_info']['stream_url'], + 'format': 'mp4', + } + formats = [format] + uploader = weibo_info['status']['user']['screen_name'] + + return { + 'id': video_id, + 'title': title, + 'uploader': uploader, + 'formats': formats + # TODO more properties (see youtube_dl/extractor/common.py) + }