爬取豆瓣图书

Bertha 。 2021-12-15 08:11 385阅读 0赞

未运行出想要的结果

#-*- coding:UTF-8 -*-
    
    import sys
    import time
    import urllib
    import urllib3
    import importlib
    import requests
    import numpy as np
    from bs4 import BeautifulSoup
    from openpyxl import Workbook
    
    importlib.reload(sys)
    
    #Some User Agents
    hds=[{'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'},\
    {'User-Agent':'Mozilla/5.0 (Windows NT 6.2) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.12 Safari/535.11'},\
    {'User-Agent': 'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Trident/6.0)'}]
    
    #function:获得标签为book_tag的所有图书信息
    #book_tag:图书标签 例如:'个人管理'
    def book_spider(book_tag):
        #初始化页数为0
        page_num = 0
        #创建图书列表
        book_list = []
        #尝试次数初始化为0
        try_times = 0
    
        while(1):
            # url='[图片]http://www.douban.com/tag/%E5%B0%8F%E8%AF%B4/book?start=0' # For Test
            url = 'http://www.douban.com/tag/'+urllib.request.quote(book_tag)+'/book?start='+str(page_num*15)
            print("url is {}".format(url));
            #休眠
            time.sleep(np.random.rand()*5)
    
            #Last Version
            try:
                req = urllib.request.Request(url,headers=hds[page_num%len(hds)])
    
                #获取到的网页代码
                source_code = urllib.request.urlopen(req).read()
    
                #强制转换成字符串
                plain_text=str(source_code)
    
    
            except (urllib.error.HTTPError,urllib.error.URLError) as e:
                print(e)
                continue #url='[图片]http://www.douban.com/tag/%E5%B0%8F%E8%AF%B4/book?start=0' # For Test #url='[图片]http://www.douban.com/tag/%E5%B0%8F%E8%AF%B4/book?start=0' # For Test
    
    
            ##Previous Version, IP is easy to be Forbidden
            #source_code = requests.get(url)
            #plain_text = source_code.text
    
            soup = BeautifulSoup(plain_text)
    
            list_soup = soup.find('div',{'class':'mod book-list'})
    
    
            try_times+=1
            if list_soup == None and try_times < 200:
                continue
            elif list_soup==None or len(list_soup)<=1:
                break #Break When no information got after 200 times requesting
    
            for book_info in list_soup.findAll('dd'):
                title = book_info.find('a',{'class':'title'}).string.strip()
                desc = book_info.find('div',{'class':'desc'}).string.strip()
                desc_list = desc.split('/')
                book_url = book_info.find('a',{'class':'title'}).get('href')
    
    
                try:
                    author_info = '作者/译者: '+'/'.join(desc_list[0:-3])
                except:
                    author_info = '作者/译者: 暂无'
                try:
                    pub_info = '出版信息：'+'/'.join(desc_list[-3:])
                except:
                    pub_info = '出版信息: 暂无'
                try:
                    rating = book_info.find('span',{'class':'rating_nums'}).string.strip()
                except:
                    rating = '0.0'
                try:
                    #people_num = book_info.findAll('span',{'class':'rating_nums'}).string.strip()
                    people_num = book_info.findAll('span')[2].string.strip()
                    people_num = get_people_num(book_url)
                    people_num = people_num.strip('人评价')
                except:
                    people_num='0'
    
                book_list.append([title,rating,people_num,author_info,pub_info])
                try_times = 0 #set 0 when got valid information
            page_num+=1
            print("Downloading Information From Page {}".format(page_num))
            print("现在的长度是",len(book_list))
        return book_list
    
    #function:获得评分等级
    def get_people_num(url):
        # url='http://book.douban.com/subject/6082808/?from=tag_all' # For Test
        try:
            req = urllib.request.Request(url,headers=hds[np.random.randint(0,len(hds))])
            source_code = urllib.request.urlopen(req).read()
            plain_text = str(source_code)
        except (urllib.error.HTTPError,urllib.error.URLError) as e:
            print(e)
        soup = BeautifulSoup(plain_text)
        people_num = soup.find('div',{'class':'rating_sum'}).findAll('span')[1].string.strip()
        return people_num
    
    #function:获取所有对应标签的图书列表
    #book_tag_lists  ['个人管理', '时间管理', '投资', '文化', '宗教']
    def do_spider(book_tag_lists):
        #创建书单列表
        book_lists=[]
        #遍历图书标签列表
        for book_tag in book_tag_lists:
            #将单个图书标签传入book_spider函数中，获得相应标签的图书信息并赋值给book_list
            book_list = book_spider(book_tag)
            #给图书信息列表按照第二个关键字（rating）降序排序
            book_list=sorted(book_list,key=lambda x:x[1],reverse=True)
            #将排好序的图书加入到书单列表中
            book_lists.append(book_list)
        return book_list
    
    #function:将图书信息读到excel中
    def print_book_lists_excel(book_lists,book_tag_lists):
        for nb in book_lists:
            print("真的醉了",nb)
        wb = Workbook()
        ws = []
        for i in range(len(book_tag_lists)):
            ws.append(wb.create_sheet(title=book_tag_lists[i]))#utf8-》unicode
        for i in range(len(book_tag_lists)):
            #序号
            count=1
            print("len of book_lists is the ",len(book_lists))
    
            for b1 in book_lists[i]:
                ws[i].append(['序号','书名','评分','评价人数','作者','出版社'])
                count+=1
                for b1 in book_tag_lists[i]:
                    print("b0 is the ",b1[0])
                    print("len is the ",len(b1))
                    ws[i].append([count,b1[0],float(b1[1]),int(b1[2]),b1[3],b1[4]])
                    count+=1
        save_path='book_list'
        for i in range(len(book_tag_lists)):
            save_path+=('-'+book_tag_lists[i])
        save_path+='.xlsx'
        print("这是我的名字:"+save_path)
        wb.save(save_path)
    #function:主函数
    def main():
            # book_tag_lists = ['心理','判断与决策','算法','数据结构','经济','历史']
            # book_tag_lists = ['传记','哲学','编程','创业','理财','社会学','佛教']
            # book_tag_lists = ['思想','科技','科学','web','股票','爱情','两性']
            # book_tag_lists = ['计算机','机器学习','linux','android','数据库','互联网']
            # book_tag_lists = ['数学']
            # book_tag_lists = ['摄影','设计','音乐','旅行','教育','成长','情感','育儿','健康','养生']
            # book_tag_lists = ['商业','理财','管理']
            # book_tag_lists = ['名著']
            # book_tag_lists = ['科普','经典','生活','心灵','文学']
            # book_tag_lists = ['科幻','思维','金融']
             #book_tag_lists = ['个人管理', '时间管理', '投资', '文化', '宗教']
            book_tag_lists = [ '文化', ]
            book_lists = do_spider(book_tag_lists)
            print_book_lists_excel(book_lists, book_tag_lists)
    main()