入门cn的烦恼,请求帮我看一下

Question

import requests
import re
main_url = 'https://www.qb5.tw/book_116663/'
main_html = requests.get(main_url).text
info_list = re.findall('
（.*?）</dd', main_html)
for inf in info_list:
    url = 'https://www.qb5.tw/book_116663/'+inf[0]
    response = requests.get(url)
    html_date = response.text
    text = re.findall('
(.*?)
', html_date)[0]
    text = text.replace(' 全本小说 www.qb5.tw，最快更新<a,href="https://www.qb5.tw/book_116663/50916243.html>星门</a>最新章节！<br><br>'</span>, <span class="hljs-string">'')
    text = text.replace(' ', ' ')
    text = inf[1]+'\n\n'+text.replace('
', '\n')
    print(text)
    open('星门.txt', mode='a', encoding='gbk').write(text)

帮我试试看看这段代码什么问题，为什么得不到我想要的东西呀

Answer 1

剩下的你自己慢慢处理吧

import requests
import re
from lxml import etree
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
main_url = 'https://www.qb5.tw/book_116663/'
main_html = requests.get(main_url,headers=headers).text
info_list = re.findall('<dd><a href="(.*?)">第', main_html)
for inf in info_list:
    print(inf)
    if len(inf)!=13:
        continue
    url = f'https://www.qb5.tw/book_116663/{inf}'
    response = requests.get(url,headers=headers)
    html_date = response.text
   
    html = etree.HTML(html_date)
    sen_list = html.xpath('//*[@id="content"]//text()')
    text=''
    for i in sen_list:
        print(i)
    break