[carambatv] Add extractor (Closes #9815)
This commit is contained in:
		
							
								
								
									
										88
									
								
								youtube_dl/extractor/carambatv.py
									
									
									
									
									
										Normal file
									
								
							
							
						
						
									
										88
									
								
								youtube_dl/extractor/carambatv.py
									
									
									
									
									
										Normal file
									
								
							@@ -0,0 +1,88 @@
 | 
			
		||||
# coding: utf-8
 | 
			
		||||
from __future__ import unicode_literals
 | 
			
		||||
 | 
			
		||||
from .common import InfoExtractor
 | 
			
		||||
from ..compat import compat_str
 | 
			
		||||
from ..utils import (
 | 
			
		||||
    float_or_none,
 | 
			
		||||
    int_or_none,
 | 
			
		||||
    try_get,
 | 
			
		||||
)
 | 
			
		||||
 | 
			
		||||
 | 
			
		||||
class CarambaTVIE(InfoExtractor):
 | 
			
		||||
    _VALID_URL = r'(?:carambatv:|https?://video1\.carambatv\.ru/v/)(?P<id>\d+)'
 | 
			
		||||
    _TESTS = [{
 | 
			
		||||
        'url': 'http://video1.carambatv.ru/v/191910501',
 | 
			
		||||
        'md5': '2f4a81b7cfd5ab866ee2d7270cb34a2a',
 | 
			
		||||
        'info_dict': {
 | 
			
		||||
            'id': '191910501',
 | 
			
		||||
            'ext': 'mp4',
 | 
			
		||||
            'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
 | 
			
		||||
            'thumbnail': 're:^https?://.*\.jpg',
 | 
			
		||||
            'duration': 2678.31,
 | 
			
		||||
        },
 | 
			
		||||
    }, {
 | 
			
		||||
        'url': 'carambatv:191910501',
 | 
			
		||||
        'only_matching': True,
 | 
			
		||||
    }]
 | 
			
		||||
 | 
			
		||||
    def _real_extract(self, url):
 | 
			
		||||
        video_id = self._match_id(url)
 | 
			
		||||
 | 
			
		||||
        video = self._download_json(
 | 
			
		||||
            'http://video1.carambatv.ru/v/%s/videoinfo.js' % video_id,
 | 
			
		||||
            video_id)
 | 
			
		||||
 | 
			
		||||
        title = video['title']
 | 
			
		||||
 | 
			
		||||
        base_url = video.get('video') or 'http://video1.carambatv.ru/v/%s/' % video_id
 | 
			
		||||
 | 
			
		||||
        formats = [{
 | 
			
		||||
            'url': base_url + f['fn'],
 | 
			
		||||
            'height': int_or_none(f.get('height')),
 | 
			
		||||
            'format_id': '%sp' % f['height'] if f.get('height') else None,
 | 
			
		||||
        } for f in video['qualities'] if f.get('fn')]
 | 
			
		||||
        self._sort_formats(formats)
 | 
			
		||||
 | 
			
		||||
        thumbnail = video.get('splash')
 | 
			
		||||
        duration = float_or_none(try_get(
 | 
			
		||||
            video, lambda x: x['annotations'][0]['end_time'], compat_str))
 | 
			
		||||
 | 
			
		||||
        return {
 | 
			
		||||
            'id': video_id,
 | 
			
		||||
            'title': title,
 | 
			
		||||
            'thumbnail': thumbnail,
 | 
			
		||||
            'duration': duration,
 | 
			
		||||
            'formats': formats,
 | 
			
		||||
        }
 | 
			
		||||
 | 
			
		||||
 | 
			
		||||
class CarambaTVPageIE(InfoExtractor):
 | 
			
		||||
    _VALID_URL = r'https?://carambatv\.ru/(?:[^/]+/)+(?P<id>[^/?#&]+)'
 | 
			
		||||
    _TEST = {
 | 
			
		||||
        'url': 'http://carambatv.ru/movie/bad-comedian/razborka-v-manile/',
 | 
			
		||||
        'md5': '',
 | 
			
		||||
        'info_dict': {
 | 
			
		||||
            'id': '191910501',
 | 
			
		||||
            'ext': 'mp4',
 | 
			
		||||
            'title': '[BadComedian] - Разборка в Маниле (Абсолютный обзор)',
 | 
			
		||||
            'thumbnail': 're:^https?://.*\.jpg$',
 | 
			
		||||
            'duration': 2678.31,
 | 
			
		||||
        },
 | 
			
		||||
    }
 | 
			
		||||
 | 
			
		||||
    def _real_extract(self, url):
 | 
			
		||||
        video_id = self._match_id(url)
 | 
			
		||||
 | 
			
		||||
        webpage = self._download_webpage(url, video_id)
 | 
			
		||||
 | 
			
		||||
        video_url = self._og_search_property('video:iframe', webpage, default=None)
 | 
			
		||||
 | 
			
		||||
        if not video_url:
 | 
			
		||||
            video_id = self._search_regex(
 | 
			
		||||
                r'(?:video_id|crmb_vuid)\s*[:=]\s*["\']?(\d+)',
 | 
			
		||||
                webpage, 'video id')
 | 
			
		||||
            video_url = 'carambatv:%s' % video_id
 | 
			
		||||
 | 
			
		||||
        return self.url_result(video_url, CarambaTVIE.ie_key())
 | 
			
		||||
@@ -110,6 +110,10 @@ from .camwithher import CamWithHerIE
 | 
			
		||||
from .canalplus import CanalplusIE
 | 
			
		||||
from .canalc2 import Canalc2IE
 | 
			
		||||
from .canvas import CanvasIE
 | 
			
		||||
from .carambatv import (
 | 
			
		||||
    CarambaTVIE,
 | 
			
		||||
    CarambaTVPageIE,
 | 
			
		||||
)
 | 
			
		||||
from .cbc import (
 | 
			
		||||
    CBCIE,
 | 
			
		||||
    CBCPlayerIE,
 | 
			
		||||
 
 | 
			
		||||
		Reference in New Issue
	
	Block a user