Python爬虫，爬取腾讯漫画实战

最新推荐文章于 2024-05-02 21:47:38 发布

weixin_30478923

最新推荐文章于 2024-05-02 21:47:38 发布

阅读量676

点赞数 1

文章标签：爬虫 python 操作系统

原文链接：http://www.cnblogs.com/lovejunjuan/p/11389241.html

版权

先上个爬取的结果图

最后的结果为每部漫画按章节保存

运行环境

IDE VS2019

Python3.7

Chrome、ChromeDriver

Chrome和ChromeDriver的版本需要相互对应

先上代码，代码非常简短，包含空行也才50行，多亏了python强大的库

import os
import time
import requests
from selenium import webdriver
from lxml import etree

def getChapterUrl(url):
    headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"
        }
    part_url = "http://ac.qq.com"
    res = requests.get(url, headers=headers)
    html=res.content.decode()
    el = etree.HTML(html)
    li_list = el.xpath('//*[@id="chapter"]/div[2]/ol[1]/li')
    for li in li_list:
            for p in li.xpath("./p"):
                for span in p.xpath("./span[@class='works-chapter-item']"):
                    item = {}
                    list_title = span.xpath("./a/@title")[0].replace(' ', '').split('：')
                    if list_title[1].startswith(('第', '序')):
                        getChapterFile(part_url + span.xpath("./a/@href")[0], list_title[0],list_title[1])

def getChapterFile(url,path1,path2):
    #path = os.path.join(path)
    #漫画名称目录
    path=os.path.join(path1)
    if not os.path.exists(path):
        os.mkdir(path)
    #章节目录
    path=path+'\\'+path2
    if not os.path.exists(path):
        os.mkdir(path)
    chrome=webdriver.Chrome()
    #"http://ac.qq.com/ComicView/index/id/505435/cid/2"
    chrome.get(url)
    time.sleep(4)
    imgs = chrome.find_elements_by_xpath("//div[@id='mainView']/ul[@id='comicContain']//img")
    for i in range(0, len(imgs)):
            js="document.getElementById('mainView').scrollTop="+str((i) * 1280)
            chrome.execute_script(js)
            time.sleep(3)
            print(imgs[i].get_attribute("src"))
            with open(path+'\\'+str(i)+'.png', 'wb') as f:
                f.write(requests.get(imgs[i].get_attribute("src")).content)
    chrome.close() 
    print('下载完成') 

if __name__ == '__main__':
    getChapterUrl('http://ac.qq.com/Comic/ComicInfo/id/505435')