yt-dlp/youtube_dl/extractor/weibo.py

155 lines
5.5 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
import json
import random as rnd
2017-12-26 09:18:35 +01:00
import re
2017-12-26 09:28:47 +01:00
from ..compat import (
compat_urllib_parse_urlencode as urlencode,
compat_urllib_request as Request,
compat_urlparse as parse,
)
2017-12-26 09:18:35 +01:00
from ..utils import (
js_to_json,
)
2017-12-26 09:38:51 +01:00
class WeiboIE(InfoExtractor):
_VALID_URL = r'https?://weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)'
_TEST = {
2017-12-26 09:38:51 +01:00
'url': 'https://weibo.com/6275294458/Fp6RGfbff?type=comment',
'info_dict': {
'id': 'Fp6RGfbff',
'ext': 'mp4',
'title': 'You should have servants to massage you,... 来自Hosico_猫 - 微博',
}
}
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',
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36',
'Upgrade-Insecure-Requests': '1',
}
# to get Referer url for genvisitor
2017-12-26 09:38:51 +01:00
webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers, note="first visit the page")
visitor_url = urlh.geturl()
data = urlencode({
"cb": "gen_callback",
"fp": '{"os":"2","browser":"Gecko57,0,0,0","fonts":"undefined","screenInfo":"1440*900*24","plugins":""}',
2017-12-26 09:38:51 +01:00
}).encode()
headers = {
2017-12-26 09:38:51 +01:00
'Accept-Encoding': 'gzip, deflate, br',
'Accept': '*/*',
'Referer': visitor_url,
}
r_genvisitor = Request(
'https://passport.weibo.com/visitor/genvisitor',
2017-12-26 09:38:51 +01:00
data=data,
headers=headers,
method='POST'
)
webpage, urlh = self._download_webpage_handle(r_genvisitor, video_id, note="gen visitor")
2017-12-26 09:38:51 +01:00
p = webpage.split("&&")[1] # split "gen_callback && gen_callback(...)"
i1 = p.find('{')
i2 = p.rfind('}')
2017-12-26 09:38:51 +01:00
j = p[i1:i2 + 1] # get JSON object
d = json.loads(j)
tid = d["data"]["tid"]
cnfd = "%03d" % d["data"]["confidence"]
param = urlencode({
'a': 'incarnate',
't': tid,
'w': 2,
'c': cnfd,
'cb': 'cross_domain',
'from': 'weibo',
'_rand': rnd.random()
2017-12-26 09:38:51 +01:00
})
gencallback_url = "https://passport.weibo.com/visitor/visitor?" + param
2017-12-26 09:38:51 +01:00
webpage, urlh = self._download_webpage_handle(gencallback_url, video_id, note="gen callback")
2017-12-26 09:38:51 +01:00
webpage, urlh = self._download_webpage_handle(url, video_id, headers=headers, note="retry to visit the page")
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')
2017-12-11 08:56:54 +01:00
video_sources_text = self._search_regex("video-sources=\\\\\"(.+?)\"", webpage, 'video_sources')
2017-12-26 09:38:51 +01:00
2017-12-11 08:56:54 +01:00
video_formats = parse.parse_qs(video_sources_text)
formats = []
supported_resolutions = ['720', '480']
for res in supported_resolutions:
f = video_formats.get(res)
if isinstance(f, list):
if len(f) > 0:
vid_url = f[0]
formats.append({
'url': vid_url,
'format': 'mp4',
'height': int(res),
2017-12-26 09:38:51 +01:00
})
2017-12-11 08:56:54 +01:00
self._sort_formats(formats)
2017-12-26 09:38:51 +01:00
uploader = self._og_search_property('nick-name', webpage, 'uploader', default=None)
return {
2017-12-26 09:38:51 +01:00
'id': video_id,
'title': title,
'uploader': uploader,
'formats': formats
# TODO more properties (see youtube_dl/extractor/common.py)
}
2017-12-26 09:18:35 +01:00
class WeiboMobileIE(InfoExtractor):
_VALID_URL = r'https?://m.weibo.cn/status/(?P<id>[0-9]+)(\?.+)?'
_TEST = {
2017-12-26 09:38:51 +01:00
'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'
}
}
2017-12-26 09:18:35 +01:00
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
2017-12-26 09:38:51 +01:00
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)
2017-12-26 09:18:35 +01:00
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'],
2017-12-26 09:38:51 +01:00
'format': 'mp4',
}
2017-12-26 09:18:35 +01:00
formats = [format]
uploader = weibo_info['status']['user']['screen_name']
return {
2017-12-26 09:38:51 +01:00
'id': video_id,
'title': title,
'uploader': uploader,
'formats': formats
# TODO more properties (see youtube_dl/extractor/common.py)
}