pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-23 04:30:10 +09:00
Code Issues Projects Releases Wiki Activity

[franceinter] Improve extraction (Closes #10538)

Browse Source
This commit is contained in:
Sergey M․ 2016-09-14 23:59:13 +07:00
parent 3e4185c396
commit 0002962f3f
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 16 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
youtube_dl/extractor/franceinter.py
View File

@ -2,10 +2,8 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..compat import compat_str
unified_timestamp, from ..utils import month_by_name
month_by_name,
)
class FranceInterIE(InfoExtractor): class FranceInterIE(InfoExtractor):
@ -18,8 +16,7 @@ class FranceInterIE(InfoExtractor):
'id': 'la-marche-de-l-histoire/la-marche-de-l-histoire-18-decembre-2013', 'id': 'la-marche-de-l-histoire/la-marche-de-l-histoire-18-decembre-2013',
'ext': 'mp3', 'ext': 'mp3',
'title': 'L’Histoire dans les jeux vidéo du 18 décembre 2013 - France Inter', 'title': 'L’Histoire dans les jeux vidéo du 18 décembre 2013 - France Inter',
'description': 'L’Histoire dans les jeux vidéo du 18 décembre 2013 par Jean Lebrun en replay sur France Inter. Retrouvez l\'émission en réécoute gratuite et abonnez-vous au podcast !', 'description': 'md5:7f2ce449894d1e585932273080fb410d',
'timestamp': 1387324800,
'upload_date': '20131218', 'upload_date': '20131218',
}, },
} }
@ -30,22 +27,28 @@ class FranceInterIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = self._search_regex( video_url = self._search_regex(
r'<button class="replay-button playable" data-is-aod="1" data-url="([^"]+)"', webpage, 'video url') r'(?s)<div[^>]+class=["\']page-diffusion["\'][^>]*>.*?<button[^>]+data-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video url', group='url')
title = self._og_search_title(webpage) title = self._og_search_title(webpage)
description = self._og_search_description(webpage) description = self._og_search_description(webpage)
extractdate = self._search_regex('(\d{2}-([a-zA-Z\s]+)-\d{4}$)', url, 'extractdate', fatal=False) upload_date_str = self._search_regex(
extractdate = extractdate.split('-') r'class=["\']cover-emission-period["\'][^>]*>[^<]+\s+(\d{1,2}\s+[^\s]+\s+\d{4})<',
extractdate = extractdate[2] + "," + str(month_by_name(extractdate[1], 'fr')) + "," + extractdate[0] webpage, 'upload date', fatal=False)
if upload_date_str:
timestamp = unified_timestamp(extractdate) upload_date_list = upload_date_str.split()
upload_date_list.reverse()
upload_date_list[1] = compat_str(month_by_name(upload_date_list[1], lang='fr'))
upload_date = ''.join(upload_date_list)
else:
upload_date = None
return { return {
'id': video_id, 'id': video_id,
'title': title, 'title': title,
'description': description, 'description': description,
'timestamp': timestamp, 'upload_date': upload_date,
'formats': [{ 'formats': [{
'url': video_url, 'url': video_url,
'vcodec': 'none', 'vcodec': 'none',