导入selenium和lxml库

from selenium import webdriver from selenium.webdriver.common.keys import Keys import time import random from lxml import etree

设置小说搜索关键词

keyword = "开挂闯异界"

创建浏览器对象

driver = webdriver.Chrome()

打开笔趣阁小说网首页

driver.get("https://www.bige3.cc/")

输入搜索关键词并点击搜索按钮

search_input = driver.find_element_by_xpath("/html/body/div[4]/div[1]/div[2]/form/input[1]") search_input.send_keys(keyword)

按回车键进行搜索

search_input.send_keys(Keys.ENTER) time.sleep(3)

依次点击小说标题打开小说

elements = driver.find_elements_by_xpath("/html/body/div[5]/div/div/div/div/div[2]/h4/a") for i in range(len(elements)): try: # 在这里执行你想要的操作，例如获取元素文本、点击元素等 elements = driver.find_elements_by_xpath("/html/body/div[5]/div/div/div/div/div[2]/h4/a") element = elements[i] print(element.text) # 打印元素文本 # 生成随机的点击延迟时间 delay = random.uniform(3, 5) time.sleep(delay) element.click() # 点击元素

    # 切换到新打开的窗口
    driver.switch_to.window(driver.window_handles[-1])
    time.sleep(3)

    # 获取每章的标题及其内容
    chapters = driver.find_elements_by_xpath("//*[@class='listmain']/dl/dd/a")
    for j in range(len(chapters)):
        try:
            chapter = chapters[j]
            chapter_title = chapter.text.replace('、', '')# 获取章节标题
            chapter_url = chapter.get_attribute("href")  # 获取章节链接
            # 打开章节链接
            driver.get(chapter_url)
            time.sleep(3)

            # 获取章节内容
            chapter_content = driver.find_element_by_xpath("//*[@id='chaptercontent']")
            html = chapter_content.get_attribute("innerHTML")
            # 使用lxml解析章节内容
            tree = etree.HTML(html)
            content = tree.xpath("string(.)")  # 获取章节内容的文本形式

            print(chapter_title)
            print(content)

            # 后退到小说目录页
            driver.back()
            time.sleep(3)

        except Exception as e:
            continue

    # 关闭当前窗口
    driver.close()

except Exception as e:
    continue

关闭浏览

driver.quit(