下面展示一些 内联代码片。
import requests
from lxml import etree
from urllib import parse
from pprint import pprint
from tqdm import tqdm
class PythonBook:
def init(self):
self.url=“https://m.jb51.net/books/list476_1.html”
self.url_page=“https://m.jb51.net/”
self.headers={ ‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36’,
‘Authorization’: ‘Bearer your_token’}
def get_book(self,url):
req=requests.get(url=url,headers=self.headers)
req.encoding="utf-8"
#print(req.text)
return req.text
def get_book_rar(self,url):
req=requests.get(url=url,headers=self.headers,stream=True)
return req.iter_content
def etree_xpath(self,req_text,xpath):
html=etree.HTML(req_text)
list_=html.xpath(xpath)
return list_
def page_url(self):
list_page=[]
for i in range(1,11):
str_url=f"https://m.jb51.net/books/list476_{i}.html"
list_page.append(str_url)
return list_page
def parse_urljoin(self,list_url):
list_book_url=[]
for url in list_url:
url_book=parse.urljoin(self.url_page,url)
list_book_url.append(url_book)
return list_book_url
def flies_book(self,book_pdf,pdf_content):
for conte in tqdm(pdf_content(chunk_size=1042)):
with open(f"python_pdf2文件/{book_pdf}","ab") as f:
if conte:
f.write(conte)
print(f"下载完成:{book_pdf}")
def main(self):
list_p=self.page_url()
for item in list_p:
try:
req=self.get_book(item)
section='//section[@class="softlist"]/a/@href'
#p='//aside/p/text()'
url_=self.etree_xpath(req,section)
#text=self.etree_xpath(req,p)
list_text=self.parse_urljoin(url_)
for book in list_text:
reqs=self.get_book(book)
h3='//article/div/p/text()'
pdf_text=self.etree_xpath(reqs,h3)[1:-2]
#print(reqs)
rar='//div[@id="downlink"]/a/@href'
list_rar=self.etree_xpath(reqs,rar)[0]
#print(list_rar)
rar_text=self.get_book_rar(list_rar)
#print(rar_text)
file_name=list_rar.split('/')[-1]
#print(file_name)
self.flies_book(file_name,rar_text)
except:
pass
pythonbook=PythonBook()
pythonbook.main()
#pythonbook.page_url()
仅供学习使用，仅供学习使
