小说爬虫（基于requests+BeautifulSoup）

最近老是写selenium的爬虫，想复习下requests + BeautifulSoup爬取网站内容。

先写一下思路： 打开网站，获取网站的首页显示的小说-------------->根据输入的内容来进行判断是否含有该小说，有，就对该小说进行访问。------------->打开含有小说目录的网页，匹配章节名称和URL---------->循环获取文本内容，并对内容进行清理，写入文本文档。

全部代码：

 1 #!/usr/bin/env python3
 2 # -*- coding: utf-8 -*-
 3 
 4 import requests
 5 import datetime
 6 from bs4 import BeautifulSoup
 7 import time
 8 def book_info():
 9     url = 'http://www.quanshuwang.com/'
10     headers = {'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36'}
11     html = requests.get(url,timeout=30,headers=headers)
12     time.sleep(2)
13     html.encoding = html.apparent_encoding
14     soup = BeautifulSoup(html.text,'html.parser')
15     #获取热门书籍
16     hot_list = soup.select('a.msgBorder')
17     hot_book = {}
18     for x in hot_list:
19         hot_book[x['title']] = x['href']
20     #print(hot_book)
21     #获取好看的书籍：
22     wonderful_list = soup.find_all(name='a',attrs={'class':'clearfix stitle'})
23     wonderful_book = {}
24     for y in wonderful_list:
25         wonderful_book[y['title']] = y['href']
26     #print(len(wonderful_list))
27     #添加到一个总的字典中。
28     book_dict = {}
29     for k,v in hot_book.items():
30         book_dict[k] = v
31     for k,v in wonderful_book.items():
32         book_dict[k] = v
33     return book_dict
34 #询问用户想看什么书
35 def search_book(book_name,book_dict):
36     if book_name in book_dict:
37         return book_dict[book_name]
38     else:
39         return '对不起，您要查询的书籍没有找到。'
40 #获取书籍的网址，并访问。
41 def down_book(url_1):
42     url = url_1
43     headers = {'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36'}
44     html2 = requests.get(url,timeout=30,headers=headers)
45     html2.encoding = html2.apparent_encoding
46     soup2 = BeautifulSoup(html2.text,'html.parser')
47     #网页中有一个开始阅读的按钮，需要对其链接进行访问，然后才能进入目录界面。
48     read_url = soup2.select('a.reader')[0]['href']
49     html3 = requests.get(read_url,timeout=30,headers=headers)
50     html3.encoding = html3.apparent_encoding
51     soup3 = BeautifulSoup(html3.text,'html.parser')
52     info_list = soup3.select('div[class="clearfix dirconone"] a')
53     catalog_dict = {}
54     for x in info_list:
55         catalog_dict[x['title']] = x['href']
56     return catalog_dict
57 #a = down_book(search_book('盗墓笔记',book_info()))
58 #print(a)
59 def write_book(book_name,dicts):
60     headers = {
61         'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36'}
62     with open('%s.txt' % book_name,'w+') as w_b:
63         for k,v in dicts.items():
64             w_b.write('\n\n\n%s \n\n\n' % k)
65             html4 = requests.get(v,timeout=30,headers=headers)
66             html4.encoding = html4.apparent_encoding
67             soup4 = BeautifulSoup(html4.text,'html.parser')
68             text_list = soup4.select('div.mainContenr')
69             sss = ''
70             for xabc in text_list:
71                 abcd = xabc.text.replace(' ','').replace('style5();','').replace('style6();','')
72                 sss += abcd
73             print(sss)
74             w_b.write(sss)
75     return w_b.close()
76 
77 start_time = datetime.datetime.now()
78 bbb = input('请输入你要查询的书籍：')
79 if search_book(bbb,book_info()) != '对不起，您要查询的书籍没有找到。':
80     a = down_book(search_book(bbb,book_info()))
81     write_book(bbb,a)
82 else:
83     print(search_book(bbb,book_info()))
84 end_time = datetime.datetime.now()
85 cha = (end_time - start_time).seconds
86 print('此次运行耗时%s秒.' % cha)

代码中都进行了注释，如果有不懂的地方，请在文章下方进行评论。

谢谢您的阅读！

 

 

 

----------------by  sniper-huohuo  -----------------

------------        知耻而后勇        --------------

转载于:https://www.cnblogs.com/sniper-huohuohuo/p/8687433.html