diff options
Diffstat (limited to 'youtube_dl/extractor/trilulilu.py')
| -rw-r--r-- | youtube_dl/extractor/trilulilu.py | 76 | 
1 files changed, 76 insertions, 0 deletions
| diff --git a/youtube_dl/extractor/trilulilu.py b/youtube_dl/extractor/trilulilu.py new file mode 100644 index 000000000..1c46156c7 --- /dev/null +++ b/youtube_dl/extractor/trilulilu.py @@ -0,0 +1,76 @@ +import json +import re +import xml.etree.ElementTree + +from .common import InfoExtractor +from ..utils import ( +    ExtractorError, +) + + +class TriluliluIE(InfoExtractor): +    _VALID_URL = r'(?x)(?:https?://)?(?:www\.)?trilulilu\.ro/video-(?P<category>[^/]+)/(?P<video_id>[^/]+)' +    _TEST = { +        u"url": u"http://www.trilulilu.ro/video-animatie/big-buck-bunny-1", +        u'file': u"big-buck-bunny-1.mp4", +        u'info_dict': { +            u"title": u"Big Buck Bunny", +            u"description": u":) pentru copilul din noi", +        }, +        # Server ignores Range headers (--test) +        u"params": { +            u"skip_download": True +        } +    } + +    def _real_extract(self, url): +        mobj = re.match(self._VALID_URL, url) +        video_id = mobj.group('video_id') + +        webpage = self._download_webpage(url, video_id) + +        title = self._og_search_title(webpage) +        thumbnail = self._og_search_thumbnail(webpage) +        description = self._og_search_description(webpage) + +        log_str = self._search_regex( +            r'block_flash_vars[ ]=[ ]({[^}]+})', webpage, u'log info') +        log = json.loads(log_str) + +        format_url = (u'http://fs%(server)s.trilulilu.ro/%(hash)s/' +                      u'video-formats2' % log) +        format_str = self._download_webpage( +            format_url, video_id, +            note=u'Downloading formats', +            errnote=u'Error while downloading formats') + +        format_doc = xml.etree.ElementTree.fromstring(format_str) +  +        video_url_template = ( +            u'http://fs%(server)s.trilulilu.ro/stream.php?type=video' +            u'&source=site&hash=%(hash)s&username=%(userid)s&' +            u'key=ministhebest&format=%%s&sig=&exp=' % +            log) +        formats = [ +            { +                'format': fnode.text, +                'url': video_url_template % fnode.text, +            } + +            for fnode in format_doc.findall('./formats/format') +        ] + +        info = { +            '_type': 'video', +            'id': video_id, +            'formats': formats, +            'title': title, +            'description': description, +            'thumbnail': thumbnail, +        } + +        # TODO: Remove when #980 has been merged +        info['url'] = formats[-1]['url'] +        info['ext'] = formats[-1]['format'].partition('-')[0] + +        return info | 
