aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/photobucket.py
blob: b4389e0b6feaf0726a4805bec674b77cd38e295b (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
from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import compat_urllib_parse


class PhotobucketIE(InfoExtractor):
    _VALID_URL = r'http://(?:[a-z0-9]+\.)?photobucket\.com/.*(([\?\&]current=)|_)(?P<id>.*)\.(?P<ext>(flv)|(mp4))'
    _TEST = {
        'url': 'http://media.photobucket.com/user/rachaneronas/media/TiredofLinkBuildingTryBacklinkMyDomaincom_zpsc0c3b9fa.mp4.html?filters[term]=search&filters[primary]=videos&filters[secondary]=images&sort=1&o=0',
        'file': 'zpsc0c3b9fa.mp4',
        'md5': '7dabfb92b0a31f6c16cebc0f8e60ff99',
        'info_dict': {
            'timestamp': 1367669341,
            'upload_date': '20130504',
            'uploader': 'rachaneronas',
            'title': 'Tired of Link Building? Try BacklinkMyDomain.com!',
        }
    }

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

        webpage = self._download_webpage(url, video_id)

        # Extract URL, uploader, and title from webpage
        self.report_extraction(video_id)
        info_json = self._search_regex(r'Pb\.Data\.Shared\.put\(Pb\.Data\.Shared\.MEDIA, (.*?)\);',
                                       webpage, 'info json')
        info = json.loads(info_json)
        url = compat_urllib_parse.unquote(self._html_search_regex(r'file=(.+\.mp4)', info['linkcodes']['html'], 'url'))
        return {
            'id': video_id,
            'url': url,
            'uploader': info['username'],
            'timestamp': info['creationDate'],
            'title': info['title'],
            'ext': video_extension,
            'thumbnail': info['thumbUrl'],
        }