爬虫 爬小说

import requests as r
import re,encodings
import time
from lxml import etree
def pa( url,name):
    headers = {
        ‘User-Agent‘: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36‘
    }
    z = r.get(url, headers = headers)
    z.encoding = ‘UTF-8‘
    html = etree.HTML(z.text)
    # 查找章节名字  
    zhangjie = html.xpath(‘//*[@id="wrapper"]/div[3]/div/div[2]/h1/text()‘)[0]

    print(zhangjie)
    # xpath 查找小说内容
    content = html.xpath(‘//*[@id="content"]/text()‘)
    content = ‘\n‘.join(content)
    with open(name, ‘a+‘, encoding="UTF-8") as txt:
        txt.write(zhangjie + "\n")
        txt.write(content)
        print(zhangjie + ":\t写入成功")



if __name__ == ‘__main__‘:
    mulu_url = ‘http://www.yuetutu.com/cbook_22694/‘
    ‘User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.61 Safari/537.36‘
    s = r.get(mulu_url)
    s.encoding = ‘utf-8‘
    html = etree.HTML(s.text)
    text = s.text
    name = (re.search(‘<h1>(.*?)</h1>‘,text)).group()
    name = (name.replace("<h1>",‘‘)).replace(‘</h1>‘,‘‘)
    name = "./%s.txt"%name
    mulu = html.xpath(‘//*[@id="list"]/dl/dd/a/@href‘)

    print(name)
    print(mulu)
    b = 1;
    for i in mulu:
        if b > 8 :
            pa(‘http://www.yuetutu.com‘+i, name)
        b= 1+b
        time.sleep(1)