豆瓣爬取图书标签

最新推荐文章于 2020-12-12 20:27:52 发布

weixin_30414155

最新推荐文章于 2020-12-12 20:27:52 发布

阅读量285

点赞数

原文链接：http://www.cnblogs.com/zhangguoxv/p/10061817.html

版权

这是我第一个全程自己动手做的项目，算得上是中小型的吧。

直接进入正题，这个项目要求是：1. 从豆瓣爬取相关图书标签； 2. 将不同种类的图书列为几个不同的列表，将各自种类的图书标签存进去； 3. 没有IP代理池，采用了延时的笨方法。

直接上代码：

import requests
import re
import xlwt
import time
import random
from requests.exceptions import RequestException

def do_spider(book_tag_lists):
    book_lists=[]
    for book_tag in book_tag_lists:
        book_list=book_spider(book_tag)
        book_lists.append(book_list)
    return book_lists


def book_spider(book_tag):
    page_num = 0
    book_list = []
    try_times = 0
    while (page_num<10):
        url = 'https://book.douban.com/tag/'+ book_tag + '?start='+ str(page_num * 20)
        # time.sleep(random.uniform(0,3))  # 0 到 3 之间的随机浮点数
        # time.sleep(random.randint(0,5))  0 到 5 之间的随机整数，包括0,5
        try:
            headers = {
                'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
                'Accept - Language': 'zh - CN, zh;q = 0.9'
            }  # 加上headers，网站认为是浏览器访问，就能爬取
            response = requests.get(url, headers=headers)
            if response.text:                 # 这5行代码是为了爬取每种类型的所有的书使用的
                response_text = response.text
            else:
                try_times+=1
                continue
        except RequestException:
            return None

        # if try_times > 200:break   # 在这儿使用了while (page_num<10)来退出

        pattern = re.compile('<li.*?<a.*?title="(.*?)".*?<div.*?pub">(.*?)</div>.*?'
                             '"rating_nums">(.*?)</span>.*?</li>', re.S)
        items = re.findall(pattern, response_text)   # 从网页中提取相关的标签
        for item in items:
            other = item[1].strip()
            other_2 = other.split('/')  # 把字符串通过'/'符号拆分为一个列表
            try:
                title = item[0]
            except:
                title = '暂无'
            try:
                author = other_2[0].strip()
            except:
                author = '暂无'
            try:
                 date = other_2[-2].strip()
            except:
                 date = '暂无'
            try:
                 rating_nums = item[2]
            except:
                 rating_nums = '暂无'
            print(title,author,date,rating_nums)
            book_list.append([title, author, date, rating_nums])
            try_times = 0
        page_num += 1
        print('Downloading Information From Page_' + str(page_num))
    return book_list

# 将爬取得内容写到Excel中
def print_book_list_excel(book_lists, book_tag_lists):
    wb = xlwt.Workbook(encoding='utf-8')
    for i in range(len(book_tag_lists)):
        ws = wb.add_sheet(book_tag_lists[i])
        ws.write(0, 1, '标题')
        ws.write(0, 2, '作者')
        ws.write(0, 3, '出版日期')
        ws.write(0, 4, '评分')
        count = 0
        for bl in book_lists[i]:
            count+=1
            ws.write(count,0,count)
            for j in range(4):
                ws.write(count,j+1,bl[j])
    wb.save('excel.xls')

def main():
    book_tag_lists = ['漫画','三毛','金庸','二战','小说','科技']
    book_lists = do_spider(book_tag_lists) # 已经调用过book_spider了
    print_book_list_excel(book_lists,book_tag_lists)

if __name__ == '__main__':
    main()