【Python|爬虫】如何爬取下一页

Question

小说只爬取了59章还有其他目录页没有爬取，
目录页总共11页只爬取了1页

```python
import requests
from lxml import etree
 
url='https://www.qb5200.la/book/116524/'
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'}
 
res=requests.get(url,headers=headers)
html=etree.HTML(res.text)
chapter_name=html.xpath("//*/dl[@class='zjlist']/dd//text()")
href=html.xpath("//*/dl[@class='zjlist']/dd/a/@href")
base_url="https://www.qb5200.la/book/116524/"
for i in range(len(chapter_name)):
    
    data=requests.get(base_url+href[i],headers=headers)
    html=etree.HTML(data.text)
    content=html.xpath("//*/div[@id='content']//text()")
    with open(f'e:/123/{chapter_name[i]}.txt', 'w',encoding="utf-8") as f:
        for d in content:
            f.write(d.replace("\xa0\xa0\xa0\xa0",'\n'))
 

```

Answer 1

很简单加个循环就行了

import requests
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'}

for n in range(1,12): 
    url=f'https://www.qb5200.la/book/116524/index_{n}.html'
    res=requests.get(url,headers=headers)
    html=etree.HTML(res.text)
    chapter_name=html.xpath("//*/dl[@class='zjlist']/dd//text()")
    href=html.xpath("//*/dl[@class='zjlist']/dd/a/@href")
    base_url="https://www.qb5200.la/book/116524/"
    for i in range(len(chapter_name)):
        data=requests.get(base_url+href[i],headers=headers)
        html=etree.HTML(data.text)
        content=html.xpath("//*/div[@id='content']//text()")
        with open(f'e:/123/{chapter_name[i]}.txt', 'w',encoding="utf-8") as f:
            for d in content:
                f.write(d.replace("\xa0\xa0\xa0\xa0",'\n'))
        print(f'"{chapter_name[i]}" 保存完毕')
        f.close()