github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

added arte.tv extractor support for subdomain ddc - Mit offenen Karten(german) Le Dessous des Cartes(france)

Browse source
This commit is contained in:
Camillo Dell'mour 2013-12-08 14:02:14 +01:00
parent 22686b91f0
commit 56a8ab7d60
2 changed files with 29 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
youtube_dl/extractor/__init__.py
View file

@ -8,6 +8,7 @@ from .arte import (
ArteTVPlus7IE, ArteTVPlus7IE,
ArteTVCreativeIE, ArteTVCreativeIE,
ArteTVFutureIE, ArteTVFutureIE,
ArteTVDDCIE,
) )
from .auengine import AUEngineIE from .auengine import AUEngineIE
from .bambuser import BambuserIE, BambuserChannelIE from .bambuser import BambuserIE, BambuserChannelIE

28
youtube_dl/extractor/arte.py
View file

@ -10,6 +10,7 @@ from ..utils import (
determine_ext, determine_ext,
get_element_by_id, get_element_by_id,
compat_str, compat_str,
get_element_by_attribute,
) )
# There are different sources of video in arte.tv, the extraction process # There are different sources of video in arte.tv, the extraction process
@ -142,7 +143,9 @@ class ArteTVPlus7IE(InfoExtractor):
def _extract_from_webpage(self, 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')
return self._extract_from_json_url(json_url, video_id, lang)
def _extract_from_json_url(self, json_url, video_id, lang):
json_info = self._download_webpage(json_url, video_id, 'Downloading info json') json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
self.report_extraction(video_id) self.report_extraction(video_id)
info = json.loads(json_info) info = json.loads(json_info)
@ -257,3 +260,28 @@ class ArteTVFutureIE(ArteTVPlus7IE):
webpage = self._download_webpage(url, anchor_id) webpage = self._download_webpage(url, anchor_id)
row = get_element_by_id(anchor_id, webpage) row = get_element_by_id(anchor_id, webpage)
return self._extract_from_webpage(row, anchor_id, lang) return self._extract_from_webpage(row, anchor_id, lang)
class ArteTVDDCIE(ArteTVPlus7IE):
IE_NAME = u'arte.tv:ddc'
_VALID_URL = r'http?://ddc\.arte\.tv/(?P<lang>emission|folge)/(?P<id>.+)'
_TEST = {
u'url': u'http://ddc.arte.tv/folge/neues-aus-mauretanien',
u'file': u'Mit offenen Karten-049881-009_PLUS7-D.flv',
u'info_dict': {
u'title': u'neues-aus-mauretanien',
},
}
def _real_extract(self, url):
video_id, lang = self._extract_url_info(url)
if lang == 'folge':
lang = 'de'
elif lang == 'emission':
lang = 'fr'
webpage = self._download_webpage(url, video_id)
scriptElement = get_element_by_attribute('class', 'visu_video_block', webpage)
script_url = self._html_search_regex(r'src="(.*?)"', scriptElement, 'script url')
javascriptPlayerGenerator = self._download_webpage(script_url, video_id, 'Download javascript player generator')
json_url = self._search_regex(r"json_url=(.*)&rendering_place.*", javascriptPlayerGenerator, 'json url')
return self._extract_from_json_url(json_url, video_id, lang)