刚学习的python，获取列表帖子

978069486

coding=utf-8

import requests
from lxml import etree
host = "https://bbs.125.la/"
def get_demo():
i = 0
while i <= 869:
i += 1

print(i)

    url = "https://bbs.125.la/forum-98-" + str(i) + ".html"
    print("=" * 40)
    print(url)
    header = {
        "Host": "bbs.125.la",
        "Connection": "keep-alive",
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400",
        "X-Requested-With": "XMLHttpRequest",
        "Accept": "*/*",
        "Referer": "https://bbs.125.la/forum-98-1.html",
    }
    cookies = {
        "Cookie": "替换成自己的cookies"
    }
    req = requests.get(url, headers=header, cookies=cookies)

    text = req.content.decode('gbk',"ignore")
    html = etree.HTML(text)
    result = html.xpath("//*[@id='threadlisttableid']/tbody/tr/th/a[2]")

    for a in result:
        str1 = a.xpath("text()")[0]
        href = a.xpath("@href")[0]
        if href.find("html") != -1:
            try:
                f.write(str1 + "----" + host + href + "\n")
                print(str1, host + href)
            except:
                print("编码有误",str1)

if name == 'main':
f = open('demo.txt', mode='w',encoding='utf-8')
get_demo()
f.close()

xuxuand

666666666666

凌云啊

python写这些东西确实方便啊

神女软件定制

建议放弃。