fix: extractor for speakerdeck.com
This commit is contained in:
committed by
Mike Fährmann
parent
c6fc0281e8
commit
f272b5d2ac
@@ -10,6 +10,7 @@
|
|||||||
|
|
||||||
from .common import Extractor, Message
|
from .common import Extractor, Message
|
||||||
from .. import text
|
from .. import text
|
||||||
|
import re
|
||||||
|
|
||||||
|
|
||||||
class SpeakerdeckPresentationExtractor(Extractor):
|
class SpeakerdeckPresentationExtractor(Extractor):
|
||||||
@@ -60,4 +61,5 @@ class SpeakerdeckPresentationExtractor(Extractor):
|
|||||||
"""Extract and return a list of all image-urls"""
|
"""Extract and return a list of all image-urls"""
|
||||||
page = self.request("https://speakerdeck.com/player/" +
|
page = self.request("https://speakerdeck.com/player/" +
|
||||||
self.presentation_id).text
|
self.presentation_id).text
|
||||||
|
page = re.sub(r"\s+", " ", page)
|
||||||
return list(text.extract_iter(page, 'js-sd-slide" data-url="', '"'))
|
return list(text.extract_iter(page, 'js-sd-slide" data-url="', '"'))
|
||||||
|
|||||||
Reference in New Issue
Block a user