NLP/wikiextractor
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix to urllib.parse.quote.

Browse Source
This commit is contained in:
attardi 2020-12-16 17:13:58 +01:00
parent ca5c40f68b
commit 1c57c06596
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
wikiextractor/extract.py
View File

@ -21,7 +21,7 @@
import re import re
import html import html
from itertools import zip_longest from itertools import zip_longest
import urllib import urllib.parse.quote as urlquote
from html.entities import name2codepoint from html.entities import name2codepoint
import logging import logging
import time import time
@ -422,7 +422,7 @@ def replaceExternalLinks(text):
def makeExternalLink(url, anchor): def makeExternalLink(url, anchor):
"""Function applied to wikiLinks""" """Function applied to wikiLinks"""
if Extractor.keepLinks: if Extractor.keepLinks:
return '<a href="%s">%s</a>' % (urllib.quote(url.encode('utf-8')), anchor) return '<a href="%s">%s</a>' % (urlquote(url.encode('utf-8')), anchor)
else: else:
return anchor return anchor
@ -492,7 +492,7 @@ def makeInternalLink(title, label):
if colon2 > 1 and title[colon + 1:colon2] not in acceptedNamespaces: if colon2 > 1 and title[colon + 1:colon2] not in acceptedNamespaces:
return '' return ''
if Extractor.keepLinks: if Extractor.keepLinks:
return '<a href="%s">%s</a>' % (urllib.quote(title), label) return '<a href="%s">%s</a>' % (urlquote(title), label)
else: else:
return label return label
@ -1615,7 +1615,7 @@ parserFunctions = {
# This function is used in some pages to construct links # This function is used in some pages to construct links
# http://meta.wikimedia.org/wiki/Help:URL # http://meta.wikimedia.org/wiki/Help:URL
'urlencode': lambda string, *rest: urllib.quote(string.encode('utf-8')), 'urlencode': lambda string, *rest: urlquote(string.encode('utf-8')),
'lc': lambda string, *rest: string.lower() if string else '', 'lc': lambda string, *rest: string.lower() if string else '',