1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-25 04:02:32 +01:00

[booru] unquote tags to fix multiple tags in urls

This commit is contained in:
Mike Fährmann 2014-12-22 16:45:58 +01:00
parent f2c68a5753
commit 2a7dbd8868
2 changed files with 4 additions and 4 deletions

4
config
View File

@ -21,5 +21,5 @@ regex0 = (?:https?://)?(?:www\.)?imgbox\.com(/.*)
regex0 = (?:https?://)?(?:www\.)?imagebam\.com/(gallery|image)/([^/]+).* regex0 = (?:https?://)?(?:www\.)?imagebam\.com/(gallery|image)/([^/]+).*
[e621] [e621]
regex0 = (?:https?://)?(?:www\.)?e621\.net/post/index/\d+/(\w+) regex0 = (?:https?://)?(?:www\.)?e621\.net/post/index/\d+/([^?]+)
regex1 = e(?:621)?[.:-_](\w.+) regex1 = e(?:621)?[.:-_](\w.+)

View File

@ -1,12 +1,13 @@
from .common import AsyncExtractor from .common import AsyncExtractor
from ..util import filename_from_url from ..util import filename_from_url
import xml.etree.ElementTree as ET import xml.etree.ElementTree as ET
import urllib.parse
class BooruExtractor(AsyncExtractor): class BooruExtractor(AsyncExtractor):
def __init__(self, match, config): def __init__(self, match, config):
AsyncExtractor.__init__(self, config) AsyncExtractor.__init__(self, config)
self.tags = match.group(1) self.tags = urllib.parse.unquote(match.group(1))
self.category = "booru" self.category = "booru"
self.params = {"tags": self.tags} self.params = {"tags": self.tags}
self.page = "page" self.page = "page"
@ -18,7 +19,6 @@ class BooruExtractor(AsyncExtractor):
root = ET.fromstring( root = ET.fromstring(
self.request(self.api_url, verify=True, params=self.params).text self.request(self.api_url, verify=True, params=self.params).text
) )
# root = tree.getroot()
if len(root) == 0: if len(root) == 0:
return return
for item in root: for item in root: