爬取贴吧上几页的内容

1.正常方法贴吧爬取

import urllib.request
import urllib.parse
baseurl=‘https://tieba.baidu.com/f?’

headers={
‘User-Agent’:
‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3706.400 SLBrowser/10.0.4040.400’}

name=input(‘请输入：’)
up=int(input(‘输入起始页：’))
end=int(input('输入末尾页： '))

kw = {‘kw’:name}
kw = urllib.parse.urlencode(kw)
for i in range(up,end):
pn=(i-1)*50
url = baseurl + kw+ ‘&pn=’ + str(pn)

req= urllib.request.Request(url,headers=headers)
res = urllib.request.urlopen(req)

# html = req.read().decode('UTF-8')
html1=res.read().decode('utf-8')

filename='第'+str(i)+'页贴吧内容'
with open(filename,'w',encoding='utf-8') as f:
    print('正在爬取第{}页'.format(i))
    f.write(html1)

2.利用函数进行贴吧爬取

import urllib.request
import urllib.parse
#读取页面
def readage(url):
headers = {‘User-Agent’:
‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3706.400 SLBrowser/10.0.4040.400’}

res = urllib.request.Request(url, headers=headers)
req = urllib.request.urlopen(res)
html = req.read().decode('utf-8')
return html

#写入文件
def writeage(filename,html):
with open(filename, ‘w’, encoding=‘utf-8’) as f:

    f.write(html)

def main():
name = input(‘请输入：’)
up = int(input(‘输入起始页：’))
end = int(input('输入末尾页： '))

kw = {'kw': name}
kw = urllib.parse.urlencode(kw)
for i in range(up, end+1):
    pn = (i - 1) * 50


baseurl = 'https://tieba.baidu.com/f?'

url = baseurl + kw + '&pn=' + str(pn)
html=readage(url)
filename='贴吧爬取2'
writeage(filename,html)

if name ==‘main’:

main()