爬取吞噬星空小说

import requests
import re

url = "https://www.777zw.net/2/2142/751765.html"


with open('tunshixingkong.txt', 'a', encoding='utf8') as f:
    for i in range(5000):
        try:
            r = requests.get(url)
            r.encoding = 'gbk'
            url = re.findall('<a href="(.*?)">下一章</a>', r.text)[0]
            url = url.split(';')[-1]
            url = re.findall('<a href="(.*?).html', url)[0]
            url = f"https://www.777zw.net/2/2142/{url}.html"
            title = re.findall('<h1>(.*?)</h1>', r.text)[0]
            content = re.findall('id="content">(.*?)</div>', r.text)[0].strip('&nbsp;').replace("<br /><br />&nbsp;&nbsp;&nbsp;&nbsp;","\n")

            f.write(title+'\n'+content+'\n'*2)
            print(f'第{i+1}章')
        except:
            print('defeat!')
            print(url)

标签：content,星空,url,text,爬取,re,吞噬,nbsp,findall
来源： https://www.cnblogs.com/xzztj/p/15861938.html