使用selenium进行爬取网络小说

最新推荐文章于 2024-05-08 21:32:09 发布

重复就是好方法

最新推荐文章于 2024-05-08 21:32:09 发布

阅读量980

点赞数

文章标签： python selenium

本文链接：https://blog.csdn.net/weixin_55633523/article/details/124207020

版权

from time import sleep
from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By

try:
    service = Service('chromedriver.exe')
    driver = webdriver.Chrome(service=service)
    driver.get('http://quanxiaoshuo.org/243825/') #小说网站

    ji = int(input('请输入要下载到的章节'))   #交互式输入章节
    for i in range(1,ji+1):
        ji = ji                             #全局变量到for循环里面必须要这样
        if i == 1:
            sleep(1)
            elements = driver.find_element(By.XPATH, f'/html/body/div[9]/div[{i}]/a').get_attribute('href')  
            driver.get(elements)
        elif i == 17:
            continue
        else:
            sleep(1)
            driver.get('http://quanxiaoshuo.org/243825/')
            elements = driver.find_element(By.XPATH, f'/html/body/div[9]/div[{i}]/a').get_attribute('href')
            driver.get(elements)
        print(f'第{i}页')
        title = driver.find_element(By.TAG_NAME, 'h1').text
        text  = driver.find_element(By.XPATH,'//*[@id="content"]').text

        print(title)
        #小说一个章节一个文档
        # with open(r'D:\workspace\book\全球高武-'+title+'.txt','a',encoding='utf-8') as f:  #下载章节目录到本地
        #     f.write('\n'+title+'\n'+text)

        #所有章节都在一个文档
        with open(r'D:\workspace\全球高武小说.txt','a', encoding='utf-8') as f:
            f.write('\n' + title + '\n' + text +'\n'+ "*"*120 + '\n')

except:
    print('错误')
finally:
    sleep(3)
    driver.quit()