当我测试它时，它一直打印出 (None, 0) 即使我使用的 url 有几个
import urllib.request as ur
def getNextlink(url):
sourceFile = ur.urlopen(url)
sourceText = sourceFile.read()
page = str(sourceText)
startLink = page.find('<a href=')
if startLink == -1:
return None, 0
startQu = page.find('"', startLink)
endQu = page.find('"', startQu+1)
url = page[startQu +1:endQu]
return url, endQu
请您参考如下方法:
你应该使用漂亮的汤，而不是它能很好地满足你的要求。下面我举个例子:
from bs4 import BeautifulSoup
import requests
def links(url):
html = requests.get(url).content
bsObj = BeautifulSoup(html, 'lxml')
links = bsObj.findAll('a')
finalLinks = set()
for link in links:
finalLinks.add(link.attrs['href'])
