Python爬虫实战：自动抓取金庸小说全集教程

核心代码逻辑解析

# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup
from urllib import request
import re
import os,time
#访问url，返回html页面
def get_html(url):
  req = request.Request(url)
  req.add_header('User-Agent','Mozilla/5.0')
  response = request.urlopen(url)
  html = response.read()
  return html
#从列表页获取小说书名和链接
def get_books(url):#根据列表页，返回此页的{书名:链接}的字典
  html = get_html(url)
  soup = BeautifulSoup(html,'lxml')
  fixed_html = soup.prettify()
  books = soup.find_all('div',attrs={'class':'bbox'})
  book_dict = {}
  for book in books:
    book_name = book.h3.a.string
    book_url = book.h3.a.get('href')
    book_dict[book_name] = book_url
  return book_dict
#根据书名链接，获取具体的章节{名称:链接} 的字典
def get_parts(url):
  html = get_html(url)
  soup = BeautifulSoup(html,'lxml')
  fixed_html = soup.prettify()
  part_urls = soup.find_all('a')
  host = "http://www.xiaoshuotxt.org"
  part_dict = {}
  for p in part_urls:
    p_url = str(p.get('href'))
    if re.search(r'\d{5}.html',p_url) and ("xiaoshuotxt" not in p_url):
      part_dict[p.string] = host + p_url
  return part_dict
#根据章节的url获取具体的章节内容
def get_txt(url):
  html = get_html(url)
  soup = BeautifulSoup(html,'lxml')
  fixed_html = soup.prettify()
  title = soup.h1.string #获取文章标题
  content = soup.find('div',attrs={'class':'zw'})
  txt = BeautifulSoup.get_text(content) #正文内容
  return txt
if __name__ == "__main__":
  root_dir= r'e:\books'
  #url = 'http://www.xiaoshuotxt.org/mingzhu/index_2.html' #第2页的小说
  url = "http://www.xiaoshuotxt.org/writer/58" #金庸的小说
  books = get_books(url)
  for book_name,book_url in books.items():
    os.mkdir(os.path.join(root_dir,book_name))
    part_dict = get_parts(book_url)
    print(book_name,"共：",len(part_dict),"章节")
    for part_name,part_url in part_dict.items():
      print("正在保存:",part_name)
      f1 = open(r'e:\books\%s\%s.txt'%(book_name,part_name),'w',encoding='utf-8')#以utf-8编码创建文件
      part_txt = get_txt(part_url)
      f1.write(str(part_txt))
      f1.close()
      time.sleep(2)