python爬取小说的代码没有执行循环

Question

想爬取这个网站的小说章节

import requests

from bs4 import BeautifulSoup

if name == 'main':
url = 'http://guoxue.lishichunqiu.com/gdxs/sanguoyanyi/' #对首页数据进行爬取
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 ('
'KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.27'}
page_text = requests.get(url=url,headers=headers).text
#在首页中解析出章节的标题和详情页的url
#1.实例化BeautifulSoup对象，需要将页面源码数据加载到该对象中
soup = BeautifulSoup(page_text,'lxml')
#解析章节标题和详情页url
li_list = soup.select('body > table:nth-child(8) > tbody > tr > td > table.box.no_doc > tbody > tr > td')
fp = open('./sanguo.txt','w',encoding='utf-8')
for li in li_list:
title = li.a.string
detail_url = li.a['href']
print(detail_url)
#对详情页发起请求，解析出章节内容
detail_page_text = requests.get(url=detail_url,headers=headers).text
#解析出详情页相关的章节内容
detail_soup = BeautifulSoup(detail_page_text,'lxml')
div_tag = detail_soup.find('div',id='content')
#解析到了章节的内容
content = div_tag.text
fp.write(title+':'+content+'\n')
print(title,'ok')

运行结果是只爬取了第一章，没有循环

试了url没什么问题，就是循环不执行，可能是title = li.a.string这条出了问题，但是我不知道怎么改

想要他执行循环爬取所有章节

Answer 1

这是按照你的改的，因为你没拿到链接。其实你这需求用re会更方便。

import requests
from bs4 import BeautifulSoup

if __name__ == '__main__':
    url = 'http://guoxue.lishichunqiu.com/gdxs/sanguoyanyi/'  # 对首页数据进行爬取
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 ('
                             'KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.27'}
    page_text = requests.get(url=url, headers=headers).text
    # print(page_text)
    # 在首页中解析出章节的标题和详情页的url
    # 1.实例化BeautifulSoup对象，需要将页面源码数据加载到该对象中
    soup = BeautifulSoup(page_text, 'lxml')
    # 提取含标题及链接的a标签
    list1 = soup.select('table.line_bottom > tbody > tr > td > table > tbody > tr > td > a')
    # print(list1)
    with open('./sanguo.txt', 'w', encoding='utf-8') as fp:
        for li in list1:
            # print(li)
            # 解析章节标题和详情页url
            title = li['title']
            detail_url = li['href']
            print(title, detail_url)
            # 对详情页发起请求，解析出章节内容
            detail_page_text = requests.get(url=detail_url, headers=headers).text
            # 解析出详情页相关的章节内容
            detail_soup = BeautifulSoup(detail_page_text, 'lxml')
            div_tag = detail_soup.find('div', id='content')
            # 解析到了章节的内容
            content = div_tag.text
            fp.write(title + ':' + content + '\n')
            print(title, 'ok')