def goahead(self,end):
# fix incomplete entity and char refs
rawdata = self.rawdata
i = 0
n = len(rawdata)
newdata=''
while i < n:
j = find(rawdata,'&',i)
if j==-1:
break
newdata = newdata + rawdata[i:j]
if charref.match(rawdata, j) or entityref.match(rawdata, j):
newdata = newdata + '&'
else:
newdata = newdata + '&'
i = j+1
self.rawdata = newdata + rawdata[i:]
# do normal parsing
try:
return HTMLParser.goahead(self,end)
except HTMLParseError:
pass
def goahead(self,end):
# fix incomplete entity and char refs
rawdata = self.rawdata
i = 0
n = len(rawdata)
newdata=''
while i < n:
j = find(rawdata,'&',i)
if j==-1:
break
newdata = newdata + rawdata[i:j]
if charref.match(rawdata, j) or entityref.match(rawdata, j):
newdata = newdata + '&'
else:
newdata = newdata + '&'
i = j+1
self.rawdata = newdata + rawdata[i:]
# do normal parsing
try:
return HTMLParser.goahead(self,end)
except HTMLParseError:
pass
def goahead(self, end):
# same as inherit except break statement in start of while loop
rawdata = self.rawdata
i = 0
n = len(rawdata)
while i < n:
if self.isImagePageFound: # added to stop searching through html after the image page is found
break
match = self.interesting.search(rawdata, i) # < or &
if match:
j = match.start()
else:
if self.cdata_elem:
break
j = n
if i < j:
self.handle_data(rawdata[i:j])
i = self.updatepos(i, j)
if i == n:
break
startswith = rawdata.startswith
if startswith("<", i):
if starttagopen.match(rawdata, i): # < + letter
k = self.parse_starttag(i)
elif startswith("</", i):
k = self.parse_endtag(i)
elif startswith("<!--", i):
k = self.parse_comment(i)
elif startswith("<?", i):
k = self.parse_pi(i)
elif startswith("<!", i):
k = self.parse_html_declaration(i)
elif (i + 1) < n:
self.handle_data("<")
k = i + 1
else:
break
if k < 0:
if not end:
break
k = rawdata.find(">", i + 1)
if k < 0:
k = rawdata.find("<", i + 1)
if k < 0:
k = i + 1
else:
k += 1
self.handle_data(rawdata[i:k])
i = self.updatepos(i, k)
elif startswith("&#", i):
match = charref.match(rawdata, i)
if match:
name = match.group()[2:-1]
self.handle_charref(name)
k = match.end()
if not startswith(";", k - 1):
k = k - 1
i = self.updatepos(i, k)
continue
else:
if ";" in rawdata[i:]: # bail by consuming &#
self.handle_data(rawdata[0:2])
i = self.updatepos(i, 2)
break
elif startswith("&", i):
match = entityref.match(rawdata, i)
if match:
name = match.group(1)
self.handle_entityref(name)
k = match.end()
if not startswith(";", k - 1):
k = k - 1
i = self.updatepos(i, k)
continue
match = incomplete.match(rawdata, i)
if match:
# match.group() will contain at least 2 chars
if end and match.group() == rawdata[i:]:
self.error("EOF in middle of entity or char ref")
# incomplete
break
elif (i + 1) < n:
# not the end of the buffer, and can't be confused
# with some other construct
self.handle_data("&")
i = self.updatepos(i, i + 1)
else:
break
else:
assert 0, "interesting.search() lied"
# end while
if end and i < n and not self.cdata_elem:
self.handle_data(rawdata[i:n])
i = self.updatepos(i, n)
self.rawdata = rawdata[i:]