aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/yahoo.py
blob: e17a39782bd2e674855dff8a5ec3112bd40158c6 (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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
import itertools
import json
import re

from .common import InfoExtractor, SearchInfoExtractor
from ..utils import (
    compat_urllib_parse,
    compat_urlparse,
    clean_html,
    int_or_none,
)


class YahooIE(InfoExtractor):
    IE_DESC = u'Yahoo screen'
    _VALID_URL = r'http://screen\.yahoo\.com/.*?-(?P<id>\d*?)\.html'
    _TESTS = [
        {
            u'url': u'http://screen.yahoo.com/julian-smith-travis-legg-watch-214727115.html',
            u'file': u'214727115.mp4',
            u'md5': u'4962b075c08be8690a922ee026d05e69',
            u'info_dict': {
                u'title': u'Julian Smith & Travis Legg Watch Julian Smith',
                u'description': u'Julian and Travis watch Julian Smith',
            },
        },
        {
            u'url': u'http://screen.yahoo.com/wired/codefellas-s1-ep12-cougar-lies-103000935.html',
            u'file': u'103000935.mp4',
            u'md5': u'd6e6fc6e1313c608f316ddad7b82b306',
            u'info_dict': {
                u'title': u'Codefellas - The Cougar Lies with Spanish Moss',
                u'description': u'Agent Topple\'s mustache does its dirty work, and Nicole brokers a deal for peace. But why is the NSA collecting millions of Instagram brunch photos? And if your waffles have nothing to hide, what are they so worried about?',
            },
        },
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        webpage = self._download_webpage(url, video_id)

        items_json = self._search_regex(r'mediaItems: ({.*?})$',
            webpage, u'items', flags=re.MULTILINE)
        items = json.loads(items_json)
        info = items['mediaItems']['query']['results']['mediaObj'][0]
        # The 'meta' field is not always in the video webpage, we request it
        # from another page
        long_id = info['id']
        return self._get_info(long_id, video_id)

    def _get_info(self, long_id, video_id):
        query = ('SELECT * FROM yahoo.media.video.streams WHERE id="%s"'
                 ' AND plrs="86Gj0vCaSzV_Iuf6hNylf2" AND region="US"'
                 ' AND protocol="http"' % long_id)
        data = compat_urllib_parse.urlencode({
            'q': query,
            'env': 'prod',
            'format': 'json',
        })
        query_result_json = self._download_webpage(
            'http://video.query.yahoo.com/v1/public/yql?' + data,
            video_id, u'Downloading video info')
        query_result = json.loads(query_result_json)
        info = query_result['query']['results']['mediaObj'][0]
        meta = info['meta']

        formats = []
        for s in info['streams']:
            format_info = {
                'width': int_or_none(s.get('width')),
                'height': int_or_none(s.get('height')),
                'tbr': int_or_none(s.get('bitrate')),
            }

            host = s['host']
            path = s['path']
            if host.startswith('rtmp'):
                format_info.update({
                    'url': host,
                    'play_path': path,
                    'ext': 'flv',
                })
            else:
                format_url = compat_urlparse.urljoin(host, path)
                format_info['url'] = format_url
                
            formats.append(format_info)

        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': meta['title'],
            'formats': formats,
            'description': clean_html(meta['description']),
            'thumbnail': meta['thumbnail'],
        }


class YahooNewsIE(YahooIE):
    IE_NAME = 'yahoo:news'
    _VALID_URL = r'http://news\.yahoo\.com/video/.*?-(?P<id>\d*?)\.html'

    _TEST = {
        u'url': u'http://news.yahoo.com/video/china-moses-crazy-blues-104538833.html',
        u'md5': u'67010fdf3a08d290e060a4dd96baa07b',
        u'info_dict': {
            u'id': u'104538833',
            u'ext': u'mp4',
            u'title': u'China Moses Is Crazy About the Blues',
            u'description': u'md5:9900ab8cd5808175c7b3fe55b979bed0',
        },
    }

    # Overwrite YahooIE properties we don't want
    _TESTS = []

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        webpage = self._download_webpage(url, video_id)
        long_id = self._search_regex(r'contentId: \'(.+?)\',', webpage, u'long id')
        return self._get_info(long_id, video_id)


class YahooSearchIE(SearchInfoExtractor):
    IE_DESC = u'Yahoo screen search'
    _MAX_RESULTS = 1000
    IE_NAME = u'screen.yahoo:search'
    _SEARCH_KEY = 'yvsearch'

    def _get_n_results(self, query, n):
        """Get a specified number of results for a query"""

        res = {
            '_type': 'playlist',
            'id': query,
            'entries': []
        }
        for pagenum in itertools.count(0): 
            result_url = u'http://video.search.yahoo.com/search/?p=%s&fr=screen&o=js&gs=0&b=%d' % (compat_urllib_parse.quote_plus(query), pagenum * 30)
            webpage = self._download_webpage(result_url, query,
                                             note='Downloading results page '+str(pagenum+1))
            info = json.loads(webpage)
            m = info[u'm']
            results = info[u'results']

            for (i, r) in enumerate(results):
                if (pagenum * 30) +i >= n:
                    break
                mobj = re.search(r'(?P<url>screen\.yahoo\.com/.*?-\d*?\.html)"', r)
                e = self.url_result('http://' + mobj.group('url'), 'Yahoo')
                res['entries'].append(e)
            if (pagenum * 30 +i >= n) or (m[u'last'] >= (m[u'total'] -1)):
                break

        return res