lxml

标签：x64   amp   firefox   XML   https   print   tree   style   main   

import urllib.request
from urllib import parse
from lxml import etree


class Tieba():
    def __init__(self):
        pass


    def sendRequest(self,url,begin,end):
        headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0"}
        for value in range(begin,end+1):
            index = value - 1 * 50
            u = "&pn="+str(index)
            fullurl = url + u
            print(fullurl)
            # request = urllib.request.Request(fullurl,headers=headers)
            # response = urllib.request.urlopen(request)
            # print(response.read())

if __name__ == "__main__":
    url = "https://tieba.baidu.com/f?"
    keyword = input("请输入搜寻的关键字 >>")
    beginPage = int(input("请输入起始页 >>"))
    endPage = int(input("请输入结束页 >>"))
    kw = parse.urlencode({"kw",keyword})
    fullurl = url + kw
    pattern = Tieba()
    pattern.sendRequest(url,beginPage,endPage)

lxml

标签：x64   amp   firefox   XML   https   print   tree   style   main   

原文地址：https://www.cnblogs.com/angle90/p/9157069.html