aboutsummaryrefslogtreecommitdiffstats
path: root/youtube_dl/extractor/weibo.py
blob: cbe0c3228babefda67619dc48605fefa4ce864dc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor

import json
import random
import re

from ..compat import (
    compat_urlparse,
)
from ..utils import (
    js_to_json,
    strip_jsonp,
    urlencode_postdata,
)


class WeiboIE(InfoExtractor):
    _VALID_URL = r'https?://weibo\.com/[0-9]+/(?P<id>[a-zA-Z0-9]+)'
    _TEST = {
        '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)
        # to get Referer url for genvisitor
        webpage, urlh = self._download_webpage_handle(url, video_id, note="first visit the page")

        visitor_url = urlh.geturl()
        headers = {
            'Referer': visitor_url
        }

        fp = {
            "os": "2",
            "browser": "Gecko57,0,0,0",
            "fonts": "undefined",
            "screenInfo": "1440*900*24",
            "plugins": ""
        }
        data = urlencode_postdata({
            "cb": "gen_callback",
            "fp": json.dumps(fp),
        })

        genvisitor_url = 'https://passport.weibo.com/visitor/genvisitor'
        webpage = self._download_webpage(genvisitor_url, video_id, data=data, headers=headers, note="gen visitor")

        p = strip_jsonp(webpage)
        i1 = p.find('{')
        i2 = p.rfind('}')
        j = p[i1:i2 + 1]  # get JSON object
        d = json.loads(j)
        tid = d["data"]["tid"]
        cnfd = "%03d" % d["data"]["confidence"]

        query = {
            'a': 'incarnate',
            't': tid,
            'w': 2,
            'c': cnfd,
            'cb': 'cross_domain',
            'from': 'weibo',
            '_rand': random.random()
        }
        gencallback_url = "https://passport.weibo.com/visitor/visitor"
        self._download_webpage(gencallback_url, video_id, note="gen callback", query=query)

        webpage = self._download_webpage(url, video_id, note="retry to visit the page")

        title = self._html_search_regex(r'<title>(.+?)</title>', webpage, 'title')

        video_sources_text = self._search_regex(r'video-sources=\\\"(.+?)\"', webpage, 'video_sources')

        video_formats = compat_urlparse.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),
                    })
        self._sort_formats(formats)
        uploader = self._og_search_property('nick-name', webpage, 'uploader', default=None)
        return {
            'id': video_id,
            'title': title,
            'uploader': uploader,
            'formats': formats
        }


class WeiboMobileIE(InfoExtractor):
    _VALID_URL = r'https?://m\.weibo\.cn/status/(?P<id>[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)
        # to get Referer url for genvisitor
        webpage = self._download_webpage(url, video_id, 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.get('status').get('page_info')
        title = weibo_info.get('status').get('status_title')
        uploader = weibo_info.get('status').get('user').get('screen_name')

        return {
            'id': video_id,
            'title': title,
            'uploader': uploader,
            'url': page_info['media_info']['stream_url']
        }