python之新手一看就懂的小说爬虫-优快云博客

本文介绍了一个简单的Python爬虫程序，用于抓取指定网站的小说章节内容并保存为本地文件。该程序使用了urllib.request和BeautifulSoup库，通过设置请求头来模拟浏览器行为，并解析HTML获取小说章节标题及正文。

晚上回来学学爬虫，记住，很多网站一般新手是爬不出来的，来个简单的，往下看：


import urllib.request
from bs4 import BeautifulSoup  #我用的pycharm需要手动导入这个包的
import lxml　　#同上



def getHtml(url,headers):
    req = urllib.request.Request(url=url, headers=headers)
    res =urllib.request.urlopen(req)
    html = res.read()
    return html

def saveTxt(path,html):
    f = open(path,'wb')
    f.write(html)

def praseHtml(currentURL,headers,path):
    # html = html.decode('utf-8')
    chapter = 0
    flag =  1
    while flag:
        chapter = chapter+1
        if chapter >= 30: #控制下载的数量，太多数据电脑要爆。
            flag = 0 #停止下载
        html = getHtml(currentURL,headers)
        savePath = path +"\\"+str(chapter)+ ".txt"
        f = open(savePath,"w")
        soup =BeautifulSoup(html,"lxml") #注意这里是lxml格式，我第一次居然写成了html，不小心就会吃亏的
        nameText = soup.find('h3',attrs={'class':'j_chapterName'})
        contentText = soup.find('div',attrs={'class':'read-content j_readContent'})
        result = nameText.getText()+'\n'+contentText.getText()
        result = result.replace('    ','\n   ')
        f = open(savePath,"w")
        f.write(result)

        nextpage = soup.find('a',attrs={'id':'j_chapterNext'})
        if next :
            currentURL = "http:" + nextpage['href']
        else:
            currentURL = None
            flag = 0

def main():
    url = "https://www.readnovel.com/chapter/22160402000540402/107513768840595159"
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.115 Safari/537.36'} #请求头自己可以再网页中查看 (f12->network->刷新)
    path = "D:\\novel"
    praseHtml(url,headers,path)

main()