使用Xpath屠戮豆瓣读书Top250

import requests
from lxml import etree
import csv
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36'
}

'''
需求分析：爬取豆瓣读书Top250
需要的信息：书名、url、作者、出版社、出版年、定价、评分、多少人评价、 评价
将爬取的信息保存为csv文件

'''
def get_info(url):
    res = requests.get(url, headers=headers)
    html = etree.HTML(res.text)
    infos = html.xpath('//tr[@class="item"]')
    for info in infos:
        book_name = info.xpath('./td/div/a/@title')[0].strip()  # 书名
        url = info.xpath('./td/div/a/@href')[0]         #url
        boo_info = info.xpath('./td/p/text()')[0].strip()
        author = boo_info.split('/')[0]  # 作者
        press = boo_info.split('/')[-3]  # 出版社
        year = boo_info.split('/')[-2]  # 出版年
        price = boo_info.split('/')[-1].strip()  # 定价
        score = info.xpath('./td/div/span[2]/text()')[0]  #评分
        ev_number = info.xpath('./td/div/span[3]/text()')[0].strip('()').strip()  #评价人数
        co_abstracts = info.xpath('./td/p/span/text()')  #内容简介
        co_abstract = co_abstracts[0] if len(co_abstracts) != 0 else "空"
        wr.writerow((book_name,url,author,press,year,price,score,ev_number,co_abstract))

if __name__ =='__main__':
    f = open('豆瓣读书.csv','wt',newline='',encoding='utf-8')
    wr = csv.writer(f)
    wr.writerow(('书名','URL','作者','出版社','出版年','定价','评分','评价人数','评价'))
    urls = ['https://book.douban.com/top250?start={}'.format(str(num)) for num in range(0,250,25)]
    for url in urls:
        get_info(url)

f.close()

ps:该程序有缺陷，有几个地方定位不是很准确

结果展示

标签：Xpath,info,xpath,url,text,豆瓣,boo,td,Top250
来源： https://www.cnblogs.com/lyqLovellx/p/15201898.html