小弟目前正在撰写计算从网页A到其他网站内连结的level，
采用的方式就是在各网页内直接抓取'href'，
当我将最高level设定在2时，没有任何问题，
但当我将其设定为3时，会跑出错误讯息如下：
UnboundLocalError: local variable 'soup' referenced before assignment
请问高手可以帮忙看看问题出在哪里吗？谢谢！
程式码如下：
import lxml.html
import urllib.request
from bs4 import BeautifulSoup
foundUrls = {}
for rootUrl in rootUrls:
foundUrls.update({rootUrl : 0})
def getProtocolAndDomainName(url):
protocolAndOther = url.split('://')
# splitting url by '://' and retrun a list
ptorocol = protocolAndOther[0]
domainName = protocolAndOther[1].split('/')[0]
# this will only return 'https://xxxxx.com'
return ptorocol + '://' + domainName
stopLevel = 3 ## 此处若改为2时不会有任何问题
rootUrls = ['http://ps.ucdavis.edu/']
foundUrls = {}
for rootUrl in rootUrls:
foundUrls.update({rootUrl : 0})
def getProtocolAndDomainName(url):
protocolAndOther = url.split('://')
ptorocol = protocolAndOther[0]
domainName = protocolAndOther[1].split('/')[0]
return ptorocol + '://' + domainName
def crawl(urls, stopLevel = 5, level=1):
nextUrls = []
if (level <= stopLevel):
for url in urls:
# need to handle urls (e.g., https) that cannot be read
try:
openedUrl = urllib.request.urlopen(url)
soup = BeautifulSoup(openedUrl, 'lxml')
except:
print('cannot read for :' + url)
for a in soup.find_all('a', href=True):
href = a['href']
if href is not None:
# for the case of a link is relative path
if '://' not in href:
href = getProtocolAndDomainName(url) + href
# check url has been already visited or not
if href not in foundUrls:
foundUrls.update({href : level})
nextUrls.append(href)
# recursive call
crawl(nextUrls, stopLevel, level + 1)
crawl(rootUrls, stopLevel)
print(foundUrls)