Python3获取豆瓣图书标签的前20本热门书籍（一）

介绍

第一篇主要获取豆瓣的大分类、大分类下的具体分类以及具体分类下的前20本热门书籍，第二篇对获取的数据进行分析。

准备

Python3.6、requests、BeautifulSoup4

演示

代码

1# -*- coding: utf-8 -*-
2# @Author: Sexy Phoenix
3# @Last Modified by:   Sexy Phoenix
4import requests
5from bs4 import BeautifulSoup, SoupStrainer
6
7#内容解析类
8class Parse:
9 
10    #解析分类
11    def parse_tags(self, content):
12
13        only_div_tags = SoupStrainer('div', 'article')
14        soup = BeautifulSoup(content, 'lxml', parse_only=only_div_tags)
15
16        category = {}
17        sub_category = {}
18
19        # 解析大分类
20        tag_title_wrapper = soup.find_all('a', 'tag-title-wrapper')
21
22        for index,tag in enumerate(tag_title_wrapper):
23            category[index] = tag.get('name')
24
25        # 解析大分类下的具体分类
26        tagCol = soup.find_all('table', "tagCol")
27        for i,tag in enumerate(soup.find_all('table', "tagCol")):
28            a = tag.find_all('a')
29            sub_category[i] = []
30            for t in a:
31                sub_category[i].append(t.string)
32
33        return category, sub_category
34    
35    #解析具体分类前20分书籍
36    def parse_detail_tag(self, content):
37
38        detail_conent = []
39        only_ul_tags = SoupStrainer('ul', 'subject-list')
40        soup = BeautifulSoup(content, 'lxml', parse_only=only_ul_tags)
41
42        for li in soup.find_all('li', 'subject-item'):
43
44            info = li.find('div', 'info')
45            title = info.h2.a.get('title')
46            star = info.find('span', 'rating_nums')
47            extra_info = info.h2.next_sibling.next_sibling.string.split('/')
48            author = extra_info[0].strip()
49            price = extra_info[-1].strip()
50            appraise = star.string
51            appraise_num = star.next_sibling.next_sibling.string.strip()
52
53            detail_conent.append({
54                'title': title,
55                'price': price,
56                'author': author,
57                'appraise':appraise,
58                'appraise_num': appraise_num
59            })
60
61        return detail_conent
62
63#内容获取类
64class Spider:
65
66    def __init__(self):
67
68        self.url = 'https://book.douban.com/tag/?view=type&icn=index-sorttags-all'
69        self.tag_url = 'https://book.douban.com/tag/'
70        self.headers = {
71            'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36'
72        }
73        self.parse = Parse()
74    
75    #获取分类HTML内容
76    def get_all_tag(self):
77
78        data = requests.get(self.url, headers=self.headers)
79        if(data.status_code == requests.codes.ok):
80            return self.parse.parse_tags(data.text)
81        else:
82            print('[ERROR]: GET Category Error')
83
84    #获取书籍HTML内容
85    def get_detail_tag(self, tag_name):
86        data = requests.get(self.tag_url + tag_name, self.headers)
87        if(data.status_code == requests.codes.ok):
88            return self.parse.parse_detail_tag(data.text)
89        else:
90            print('[ERROR]: GET Sub Category Error')
91
92    #显示
93    def show(self):
94
95        category, sub_category = self.get_all_tag()
96        print('豆瓣大分类：')
97        for index,value in category.items():
98            i = index + 1
99            print("{0}、{1}".format(i, value))
100        try:
101            key = int(input('请输入您选择的大分类：')) - 1
102            sub_cate = sub_category[key]
103            for index in range(len(sub_cate)):
104                i = index + 1
105                print("{0}、{1}".format(i, sub_cate[index]))
106            try:
107                sub_key  = int(input('请输入您选择的具体分类：')) - 1
108                tag_name = sub_cate[sub_key]
109                detail_content = self.get_detail_tag(tag_name)
110
111                for book in detail_content:
112                    print('\n')
113                    print(book['title'])
114                    print("作者：{0}, 价格：{1}, 评分：{2}{3}".format(book['author'],book['price'], book['appraise'], book['appraise_num']))
115                    print('='*50)
116
117            except:
118                print('[ERROR]: 具体分类选择错误')
119        except:
120            print('[ERROR]: 大分类选择错误')
121
122#入口
123if __name__ == '__main__':
124    spider = Spider()
125    spider.show()