快捷導(dǎo)航

python實(shí)現(xiàn)爬蟲(chóng)抓取小說(shuō)功能示例【抓取金庸小說(shuō)】

更新時(shí)間：2019年08月09日 10:32:44 作者：zhizunyu2009

這篇文章主要介紹了python實(shí)現(xiàn)爬蟲(chóng)抓取小說(shuō)功能,結(jié)合具體實(shí)例形式分析了使用Python爬蟲(chóng)抓取金庸小說(shuō)的具體操作技巧,需要的朋友可以參考下

本文實(shí)例講述了python實(shí)現(xiàn)爬蟲(chóng)抓取小說(shuō)功能。分享給大家供大家參考，具體如下：

# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup
from urllib import request
import re
import os,time
#訪問(wèn)url，返回html頁(yè)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
#從列表頁(yè)獲取小說(shuō)書(shū)名和鏈接
def get_books(url):#根據(jù)列表頁(yè)，返回此頁(yè)的{書(shū)名:鏈接}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
#根據(jù)書(shū)名鏈接，獲取具體的章節(jié){名稱(chēng):鏈接} 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
#根據(jù)章節(jié)的url獲取具體的章節(jié)內(nèi)容
def get_txt(url):
  html = get_html(url)
  soup = BeautifulSoup(html,'lxml')
  fixed_html = soup.prettify()
  title = soup.h1.string #獲取文章標(biāo)題
  content = soup.find('div',attrs={'class':'zw'})
  txt = BeautifulSoup.get_text(content) #正文內(nèi)容
  return txt
if __name__ == "__main__":
  root_dir= r'e:\books'
  #url = 'http://www.xiaoshuotxt.org/mingzhu/index_2.html' #第2頁(yè)的小說(shuō)
  url = "http://www.xiaoshuotxt.org/writer/58" #金庸的小說(shuō)
  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),"章節(jié)")
    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u(píng)tf-8編碼創(chuàng)建文件
      part_txt = get_txt(part_url)
      f1.write(str(part_txt))
      f1.close()
      time.sleep(2)

運(yùn)行效果：