I wrote a crawler to fetch information out of an Q&A website. Since not all the fields are presented in a page all the time, I used multiple try-excepts to handle the situation.
def answerContentExtractor( loginSession, questionLinkQueue , answerContentList) :
while True:
URL = questionLinkQueue.get()
try:
response = loginSession.get(URL,timeout = MAX_WAIT_TIME)
raw_data = response.text
#These fields must exist, or something went wrong...
questionId = re.findall(REGEX,raw_data)[0]
answerId = re.findall(REGEX,raw_data)[0]
title = re.findall(REGEX,raw_data)[0]
except requests.exceptions.Timeout ,IndexError:
print >> sys.stderr, URL + " extraction error..."
questionLinkQueue.task_done()
continue
try:
questionInfo = re.findall(REGEX,raw_data)[0]
except IndexError:
questionInfo = ""
try:
answerContent = re.findall(REGEX,raw_data)[0]
except IndexError:
answerContent = ""
result = {
'questionId' : questionId,
'answerId' : answerId,
'title' : title,
'questionInfo' : questionInfo,
'answerContent': answerContent
}
answerContentList.append(result)
questionLinkQueue.task_done()
And this code, sometimes, may or may not, gives the following exception during runtime:
UnboundLocalError: local variable 'IndexError' referenced before assignment
The line number indicates the error occurs at the second except IndexError:
Thanks everyone for your suggestions, Would love to give the marks that you deserve, too bad I can only mark one as the correct answer...