administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 03:10:38 +00:00
Code Issues Projects Releases Wiki Activity

[dw] add support for article pages(closes #8790)

Browse Source
This commit is contained in:
remitamine 2016-03-12 08:33:22 +01:00
parent 91d6aafb48
commit 36bb63e084
2 changed files with 35 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
youtube_dl/extractor/__init__.py
View File

@ -189,7 +189,10 @@ from .dumpert import DumpertIE
from .defense import DefenseGouvFrIE
from .discovery import DiscoveryIE
from .dropbox import DropboxIE
from .dw import DWIE
from .dw import (
DWIE,
DWArticleIE,
)
from .eagleplatform import EaglePlatformIE
from .ebaumsworld import EbaumsWorldIE
from .echomsk import EchoMskIE

36
youtube_dl/extractor/dw.py
View File

@ -3,9 +3,11 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import int_or_none
from ..compat import compat_urlparse
class DWIE(InfoExtractor):
IE_NAME = 'dw'
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)'
_TESTS = [{
# video
@ -32,16 +34,15 @@ class DWIE(InfoExtractor):
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
media_id = self._match_id(url)
webpage = self._download_webpage(url, media_id)
hidden_inputs = self._hidden_inputs(webpage)
title = hidden_inputs['media_title']
formats = []
if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
formats = self._extract_smil_formats(
'http://www.dw.com/smil/v-%s' % video_id, video_id,
'http://www.dw.com/smil/v-%s' % media_id, media_id,
transform_source=lambda s: s.replace(
'rtmp://tv-od.dw.de/flash/',
'http://tv-download.dw.de/dwtv_video/flv/'))
@ -49,7 +50,7 @@ class DWIE(InfoExtractor):
formats = [{'url': hidden_inputs['file_name']}]
return {
'id': video_id,
'id': media_id,
'title': title,
'description': self._og_search_description(webpage),
'thumbnail': hidden_inputs.get('preview_image'),
@ -57,3 +58,28 @@ class DWIE(InfoExtractor):
'upload_date': hidden_inputs.get('display_date'),
'formats': formats,
}
class DWArticleIE(InfoExtractor):
IE_NAME = 'dw:article'
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
_TEST = {
'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009',
'md5': '8ca657f9d068bbef74d6fc38b97fc869',
'info_dict': {
'id': '19105868',
'ext': 'mp4',
'title': 'The harsh life of refugees in Idomeni',
'description': 'md5:196015cc7e48ebf474db9399420043c7',
'upload_date': '20160310',
}
}
def _real_extract(self, url):
article_id = self._match_id(url)
webpage = self._download_webpage(url, article_id)
hidden_inputs = self._hidden_inputs(webpage)
media_id = hidden_inputs['media_id']
media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url')
media_url = compat_urlparse.urljoin(url, media_path)
return self.url_result(media_url, 'DW', media_id)