Beginner crawler - biqu Pavilion crawler

import requests
from lxml import etree
base_url=input(“ Please enter a novel url：”) # Like spring feast url by https://www.xbiquge.la/20/20671/
headers={
“User-Agent”:“Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:101.0) Gecko/20100101 Firefox/101.0”
}
response=requests.get(base_url,headers=headers)
r=response.content.decode()
r1=etree.HTML # String format html The fragment is parsed into html file
r2=r1.xpath(‘//[@id=“info”]/h1/text()‘) # Get the name of the novel
r3=r1.xpath(’//[@id=“list”]/dl/dd/a/text()’) # Get the title of each chapter of the novel
r4=r1.xpath(‘//[@id=“list”]/dl/dd/a/@href’) # Get links to each chapter
r5=r1.xpath('//[@id=“info”]/p[1]/text()’) # Get the author's name
r6=r1.xpath(‘//[@id=“intro”]/p[2]/text()‘) # Get the copy
r7=’‘.join(r5).split(’：‘)[1] # Get the author's name
chapter_list=[]
for i in r4:
url=“https://www.xbiquge.la”+i
chapter_list.append(url) # Synthesize each chapter url
for i in r2:
title=’{}by{}.txt’.format(i,r7) # When getting and saving txt Name
content_list=[]
with open(title,“a”,encoding=“utf-8”) as f:
f.writelines(r6)
f.write(‘\n’)
for (x,y) in zip(chapter_list,r3):
response2=requests.get(x)
res=response2.content.decode()
res1=etree.HTML(res)
res3=res1.xpath('//[@id=“content”]/text()’) # Get the content of each chapter
f.writelines(y)# Write the title of each chapter
f.write(‘\n’)
f.writelines(res3)# Write the content of each chapter
f.write(‘\n’)
print(“{} Collection completed , common {} chapter ”.format(title,len(chapter_list)))