python xpath匹配 + selenium模拟点击保存到txt

最新推荐文章于 2025-07-11 15:29:41 发布

原创最新推荐文章于 2025-07-11 15:29:41 发布 · 789 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#python #xpath #selenium

python 专栏收录该内容

13 篇文章

订阅专栏

本文深入探讨了使用Python进行网络爬虫的技术实现，包括requests库的HTTP请求管理、BeautifulSoup和lxml库的网页解析、Selenium库的浏览器自动化操作以及pymysql库的数据库交互。通过具体的代码实例，详细讲解了如何从起点URL递归抓取多个层级的网页链接，解析并存储网页内容。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import requests
import os
from bs4 import BeautifulSoup
from lxml import etree
import time
import pymysql
from selenium import webdriver
import sys
sys.setrecursionlimit(100000)

header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36',
}
res = 'https://m.qidian.com'


def pub(u, pa):
    cont = requests.get(u, header)
    home = etree.HTML(cont.text.encode('utf8'))
    ty = home.xpath(pa)
    return ty

//  qd/1/2/3循环 获取链接  
def qd(res):
    ty = pub(res, '//nav[@class="home-nav"]/a/@href')
    for i in ty:
        qd1(res + i)
        return


def qd1(url):
    ty = pub(url, '//div[@class="sort-li-detail"]/a/@href')
    for i in ty:
        qd2(res + i)
        return


def qd2(url):
    ty = pub(url, '//*[@id="books-"]/li/a/@href')
    for i in ty:
        qd3(res + i)
        return


def qd3(url):
    ty = pub(url, '//*[@id="btnReadBook"]/@href')
    for i in ty:
        qd4(res + i)
        return

// 模拟点击开始
driver = webdriver.Chrome(
    r"D:\Anaconda3\pkgs\selenium-3.141.0-py37he774522_0\Lib\site-packages\selenium\webdriver\chrome\chromedriver.exe")


def qd4(url):
    ty = pub(url, '//*[@id="btnLoadNextChapter"]')
    if ty:
        driver.get(url)
        cli(c=1)


def cli(c):
    path = driver.find_element_by_xpath("//*[@id='btnLoadNextChapter']")
    home = etree.HTML(driver.page_source)
    tit = home.xpath('//*[@id="chapterContent"]/section[{}]/h3/text()'.format(c))
    jz = home.xpath('//*[@id="chapterContent"]/section[{}]/p/text()'.format(c))
    name = home.xpath('//*[@id="readCover"]/div[1]/div[1]/h2/text()')
    title = tit + jz
	//循环存入txt
    for i in title:
        with open('{}.txt'.format(name[0]), 'a') as f:
            f.write(i + '\n')
    if path:
        driver.execute_script("arguments[0].click();", path)
        time.sleep(2)
        cli(c+1)


if __name__ == '__main__':
    qd(res)