Archives/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-17 15:25:49 +00:00
Code Issues Projects Releases Wiki Activity

[dw] Support documentaries (closes #9475)

Browse Source
This commit is contained in:
Yen Chi Hsuan 2016-05-26 22:48:47 +08:00
parent 5950cb1d6d
commit ac88d2316e
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
1 changed files with 24 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
youtube_dl/extractor/dw.py
View File

@ -2,13 +2,16 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import (
int_or_none,
unified_strdate,
)
from ..compat import compat_urlparse from ..compat import compat_urlparse
class DWIE(InfoExtractor): class DWIE(InfoExtractor):
IE_NAME = 'dw' IE_NAME = 'dw'
_VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+av-(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
# video # video
'url': 'http://www.dw.com/en/intelligent-light/av-19112290', 'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
@ -31,6 +34,16 @@ class DWIE(InfoExtractor):
'description': 'md5:bc9ca6e4e063361e21c920c53af12405', 'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
'upload_date': '20160311', 'upload_date': '20160311',
} }
}, {
'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798',
'md5': '56b6214ef463bfb9a3b71aeb886f3cf1',
'info_dict': {
'id': '19274438',
'ext': 'mp4',
'title': 'Welcome to the 90s – Hip Hop',
'description': 'Welcome to the 90s - The Golden Decade of Hip Hop',
'upload_date': '20160521',
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -38,6 +51,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, media_id) webpage = self._download_webpage(url, media_id)
hidden_inputs = self._hidden_inputs(webpage) hidden_inputs = self._hidden_inputs(webpage)
title = hidden_inputs['media_title'] title = hidden_inputs['media_title']
media_id = hidden_inputs.get('media_id') or media_id
if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1': if hidden_inputs.get('player_type') == 'video' and hidden_inputs.get('stream_file') == '1':
formats = self._extract_smil_formats( formats = self._extract_smil_formats(
@ -49,13 +63,20 @@ def _real_extract(self, url):
else: else:
formats = [{'url': hidden_inputs['file_name']}] formats = [{'url': hidden_inputs['file_name']}]
upload_date = hidden_inputs.get('display_date')
if not upload_date:
upload_date = self._html_search_regex(
r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage,
'upload date', default=None)
upload_date = unified_strdate(upload_date)
return { return {
'id': media_id, 'id': media_id,
'title': title, 'title': title,
'description': self._og_search_description(webpage), 'description': self._og_search_description(webpage),
'thumbnail': hidden_inputs.get('preview_image'), 'thumbnail': hidden_inputs.get('preview_image'),
'duration': int_or_none(hidden_inputs.get('file_duration')), 'duration': int_or_none(hidden_inputs.get('file_duration')),
'upload_date': hidden_inputs.get('display_date'), 'upload_date': upload_date,
'formats': formats, 'formats': formats,
} }