MarcoBuster/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-12 07:49:35 +01:00
Code Issues Projects Releases Wiki Activity

[arte] Add an extractor for future.arte.tv (closes #1593)

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-10-13 14:21:13 +02:00
parent c40f5cf45c
commit 69a0c470b5
2 changed files with 30 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
youtube_dl/extractor/__init__.py
View File

@ -6,6 +6,7 @@
ArteTvIE, ArteTvIE,
ArteTVPlus7IE, ArteTVPlus7IE,
ArteTVCreativeIE, ArteTVCreativeIE,
ArteTVFutureIE,
) )
from .auengine import AUEngineIE from .auengine import AUEngineIE
from .bandcamp import BandcampIE from .bandcamp import BandcampIE

31
youtube_dl/extractor/arte.py
View File

@ -1,3 +1,4 @@
# encoding: utf-8
import re import re
import json import json
import xml.etree.ElementTree import xml.etree.ElementTree
@ -8,6 +9,7 @@
find_xpath_attr, find_xpath_attr,
unified_strdate, unified_strdate,
determine_ext, determine_ext,
get_element_by_id,
) )
# There are different sources of video in arte.tv, the extraction process # There are different sources of video in arte.tv, the extraction process
@ -126,14 +128,21 @@ class ArteTVPlus7IE(InfoExtractor):
IE_NAME = u'arte.tv:+7' IE_NAME = u'arte.tv:+7'
_VALID_URL = r'https?://www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?' _VALID_URL = r'https?://www\.arte.tv/guide/(?P<lang>fr|de)/(?:(?:sendungen|emissions)/)?(?P<id>.*?)/(?P<name>.*?)(\?.*)?'
def _real_extract(self, url): @classmethod
mobj = re.match(self._VALID_URL, url) def _extract_url_info(cls, url):
mobj = re.match(cls._VALID_URL, url)
lang = mobj.group('lang') lang = mobj.group('lang')
# This is not a real id, it can be for example AJT for the news # This is not a real id, it can be for example AJT for the news
# http://www.arte.tv/guide/fr/emissions/AJT/arte-journal # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
video_id = mobj.group('id') video_id = mobj.group('id')
return video_id, lang
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
return self._extract_from_webpage(webpage, video_id, lang)
def _extract_from_webpage(self, webpage, video_id, lang):
json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url') json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
json_info = self._download_webpage(json_url, video_id, 'Downloading info json') json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
@ -202,3 +211,21 @@ class ArteTVCreativeIE(ArteTVPlus7IE):
}, },
} }
class ArteTVFutureIE(ArteTVPlus7IE):
IE_NAME = u'arte.tv:future'
_VALID_URL = r'https?://future\.arte\.tv/(?P<lang>fr|de)/(thema|sujet)/.*?#article-anchor-(?P<id>\d+)'
_TEST = {
u'url': u'http://future.arte.tv/fr/sujet/info-sciences#article-anchor-7081',
u'file': u'050940-003.mp4',
u'info_dict': {
u'title': u'Les champignons au secours de la planète',
},
}
def _real_extract(self, url):
anchor_id, lang = self._extract_url_info(url)
webpage = self._download_webpage(url, anchor_id)
row = get_element_by_id(anchor_id, webpage)
return self._extract_from_webpage(row, anchor_id, lang)