mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-27 18:41:29 +00:00
Move infoq into its own file
This commit is contained in:
parent
cbf46c737c
commit
fda7d31aa0
|
@ -31,6 +31,7 @@
|
||||||
from .extractor.generic import GenericIE
|
from .extractor.generic import GenericIE
|
||||||
from .extractor.googleplus import GooglePlusIE
|
from .extractor.googleplus import GooglePlusIE
|
||||||
from .extractor.googlesearch import GoogleSearchIE
|
from .extractor.googlesearch import GoogleSearchIE
|
||||||
|
from .extractor.infoq import InfoQIE
|
||||||
from .extractor.metacafe import MetacafeIE
|
from .extractor.metacafe import MetacafeIE
|
||||||
from .extractor.myvideo import MyVideoIE
|
from .extractor.myvideo import MyVideoIE
|
||||||
from .extractor.statigram import StatigramIE
|
from .extractor.statigram import StatigramIE
|
||||||
|
@ -44,49 +45,6 @@
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
class InfoQIE(InfoExtractor):
|
|
||||||
"""Information extractor for infoq.com"""
|
|
||||||
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
|
|
||||||
|
|
||||||
def _real_extract(self, url):
|
|
||||||
mobj = re.match(self._VALID_URL, url)
|
|
||||||
if mobj is None:
|
|
||||||
raise ExtractorError(u'Invalid URL: %s' % url)
|
|
||||||
|
|
||||||
webpage = self._download_webpage(url, video_id=url)
|
|
||||||
self.report_extraction(url)
|
|
||||||
|
|
||||||
# Extract video URL
|
|
||||||
mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
|
|
||||||
if mobj is None:
|
|
||||||
raise ExtractorError(u'Unable to extract video url')
|
|
||||||
real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
|
|
||||||
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
|
|
||||||
|
|
||||||
# Extract title
|
|
||||||
video_title = self._search_regex(r'contentTitle = "(.*?)";',
|
|
||||||
webpage, u'title')
|
|
||||||
|
|
||||||
# Extract description
|
|
||||||
video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
|
|
||||||
webpage, u'description', fatal=False)
|
|
||||||
|
|
||||||
video_filename = video_url.split('/')[-1]
|
|
||||||
video_id, extension = video_filename.split('.')
|
|
||||||
|
|
||||||
info = {
|
|
||||||
'id': video_id,
|
|
||||||
'url': video_url,
|
|
||||||
'uploader': None,
|
|
||||||
'upload_date': None,
|
|
||||||
'title': video_title,
|
|
||||||
'ext': extension, # Extension is always(?) mp4, but seems to be flv
|
|
||||||
'thumbnail': None,
|
|
||||||
'description': video_description,
|
|
||||||
}
|
|
||||||
|
|
||||||
return [info]
|
|
||||||
|
|
||||||
class MixcloudIE(InfoExtractor):
|
class MixcloudIE(InfoExtractor):
|
||||||
"""Information extractor for www.mixcloud.com"""
|
"""Information extractor for www.mixcloud.com"""
|
||||||
|
|
||||||
|
|
50
youtube_dl/extractor/infoq.py
Normal file
50
youtube_dl/extractor/infoq.py
Normal file
|
@ -0,0 +1,50 @@
|
||||||
|
import base64
|
||||||
|
import re
|
||||||
|
|
||||||
|
from .common import InfoExtractor
|
||||||
|
from ..utils import (
|
||||||
|
compat_urllib_parse,
|
||||||
|
|
||||||
|
ExtractorError,
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
|
class InfoQIE(InfoExtractor):
|
||||||
|
_VALID_URL = r'^(?:https?://)?(?:www\.)?infoq\.com/[^/]+/[^/]+$'
|
||||||
|
|
||||||
|
def _real_extract(self, url):
|
||||||
|
mobj = re.match(self._VALID_URL, url)
|
||||||
|
|
||||||
|
webpage = self._download_webpage(url, video_id=url)
|
||||||
|
self.report_extraction(url)
|
||||||
|
|
||||||
|
# Extract video URL
|
||||||
|
mobj = re.search(r"jsclassref ?= ?'([^']*)'", webpage)
|
||||||
|
if mobj is None:
|
||||||
|
raise ExtractorError(u'Unable to extract video url')
|
||||||
|
real_id = compat_urllib_parse.unquote(base64.b64decode(mobj.group(1).encode('ascii')).decode('utf-8'))
|
||||||
|
video_url = 'rtmpe://video.infoq.com/cfx/st/' + real_id
|
||||||
|
|
||||||
|
# Extract title
|
||||||
|
video_title = self._search_regex(r'contentTitle = "(.*?)";',
|
||||||
|
webpage, u'title')
|
||||||
|
|
||||||
|
# Extract description
|
||||||
|
video_description = self._html_search_regex(r'<meta name="description" content="(.*)"(?:\s*/)?>',
|
||||||
|
webpage, u'description', fatal=False)
|
||||||
|
|
||||||
|
video_filename = video_url.split('/')[-1]
|
||||||
|
video_id, extension = video_filename.split('.')
|
||||||
|
|
||||||
|
info = {
|
||||||
|
'id': video_id,
|
||||||
|
'url': video_url,
|
||||||
|
'uploader': None,
|
||||||
|
'upload_date': None,
|
||||||
|
'title': video_title,
|
||||||
|
'ext': extension, # Extension is always(?) mp4, but seems to be flv
|
||||||
|
'thumbnail': None,
|
||||||
|
'description': video_description,
|
||||||
|
}
|
||||||
|
|
||||||
|
return [info]
|
Loading…
Reference in a new issue