1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-27 23:56:51 +01:00

[RTBFVideo] Add new extractor

This commit is contained in:
Nicolas Évrard 2014-04-28 20:32:13 +02:00
parent 8a7a4a9796
commit 201e3c99b9
2 changed files with 50 additions and 0 deletions

View File

@ -210,6 +210,7 @@ from .ringtv import RingTVIE
from .ro220 import Ro220IE
from .rottentomatoes import RottenTomatoesIE
from .roxwel import RoxwelIE
from .rtbf import RTBFVideoIE
from .rtlnow import RTLnowIE
from .rts import RTSIE
from .rtve import RTVEALaCartaIE

View File

@ -0,0 +1,49 @@
# coding: utf-8
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import clean_html
class RTBFVideoIE(InfoExtractor):
_VALID_URL = r'https?://www.rtbf.be/video/(?P<title>[^?]+)\?.*id=(?P<id>[0-9]+)'
_TEST = {
'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
'md5': '799f334ddf2c0a582ba80c44655be570',
'info_dict': {
'id': '1921274',
'ext': 'mp4',
'title': 'Les Diables au coeur (épisode 2)',
'duration': 3099,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
# TODO more code goes here, for example ...
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(
r'<meta property="og:description" content="([^"]*)"',
webpage, 'title', mobj.group('title'))
print title
iframe_url = self._html_search_regex(r'<iframe [^>]*src="([^"]+)"',
webpage, 'iframe')
iframe = self._download_webpage(iframe_url, video_id)
data_video_idx = iframe.find('data-video')
next_data_idx = iframe.find('data-', data_video_idx + 1)
json_data_start = data_video_idx + len('data-video=') + 1
json_data_end = next_data_idx - 2
video_data = json.loads(clean_html(iframe[json_data_start:json_data_end]))
return {
'id': video_id,
'title': title,
'url': video_data['data']['downloadUrl'],
'duration': video_data['data']['duration'],
}