RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

escape nodename in xmliter regex

This commit is contained in:
Νικόλαος-Διγενής Καραγιάννης 2015-10-07 14:47:23 +03:00
parent d66efb13ba
commit f56062d045
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
scrapy/utils/iterators.py
View File

@ -25,8 +25,10 @@ def xmliter(obj, nodename):
- a unicode string
- a string encoded as utf-8
"""
HEADER_START_RE = re.compile(r'^(.*?)<\s*%s(?:\s|>)' % nodename, re.S)
HEADER_END_RE = re.compile(r'<\s*/%s\s*>' % nodename, re.S)
nodename_patt = re.escape(nodename)
HEADER_START_RE = re.compile(r'^(.*?)<\s*%s(?:\s|>)' % nodename_patt, re.S)
HEADER_END_RE = re.compile(r'<\s*/%s\s*>' % nodename_patt, re.S)
text = _body_or_str(obj)
header_start = re.search(HEADER_START_RE, text)
@ -34,7 +36,7 @@ def xmliter(obj, nodename):
header_end = re_rsearch(HEADER_END_RE, text)
header_end = text[header_end[1]:].strip() if header_end else ''
r = re.compile(r"<%s[\s>].*?</%s>" % (nodename, nodename), re.DOTALL)
r = re.compile(r"<{0}[\s>].*?</{0}>".format(nodename_patt), re.DOTALL)
for match in r.finditer(text):
nodetext = header_start + match.group() + header_end
yield Selector(text=nodetext, type='xml').xpath('//' + nodename)[0]