python3贴吧_python3爬取百度贴吧

import urllib

import urllib.request

def loadPage(url,filename):

"""

作用：根据url发送请求=，获取服务器响应文件

url：需要爬去的url

filename:处理得文件名

"""

print("正在下载" + filename)

headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"}

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

return urllib.request.urlopen(req).read()

def writePage(html,filename):

"""

作用:将HTML内容写入到本地

html:服务器响应得文件内容

"""

print("正在保存" + filename)

#文件写入

with open(filename,"wb") as f:

f.write(html)

print ("_" * 30)

def tiebaSpider(fullurl,beginPage,endPage):

"""

作用：贴吧爬虫调度器，负责处理每个页面得url

url：贴吧url的前部分

beginPage：起始页

endPage：结束页

"""

for page in range(beginPage,endPage + 1):

pn = (page - 1) * 50

filename = "第" + str(page) + "页.html"

print(filename)

fullurl = url + "&pn=" + str(pn)

html = loadPage(fullurl,filename)

writePage(html,filename)

print("谢谢使用")

if __name__ =="__main__":

kw = input("请输入需要爬取得吧名：")

beginPage = int(input("请输入起始页："))

endPage = int(input("请输入结束页："))

url = "http://tieba.baidu.com/f?"

key = urllib.parse.urlencode({"kw":kw})

fullurl = url + key

tiebaSpider(fullurl, beginPage, endPage)