爬虫当当网前500书籍

佚名 6年前 (2019-05-08) 随笔 1812人围观抢沙发百度已收录

import requests
import re
import json

def request_dandan(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
    except requests.RequestException:
        return None


def parse_result(html):
    pattern = re.compile('<li>.*?list_num.*?(\d+).</div>.*?<img src="(.*?)".*?class="name".*?title="(.*?)">.*?class="star">.*?class="tuijian">(.*?)</span>.*?class="publisher_info">.*?target="_blank">(.*?)</a>.*?class="biaosheng">.*?<span>(.*?)</span></div>.*?<p><span\sclass="price_n">¥(.*?)</span>.*?</li>',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield {
            'range': item[0],
            'iamge': item[1],
            'title': item[2],
            'recommend': item[3],
            'author': item[4],
            'times': item[5],
            'price': item[6]
        }


def write_item_to_file(item):
    print('开始写入数据 ====> ' + str(item))
    with open('book.txt', 'a', encoding='UTF-8') as f:
        f.write(json.dumps(item, ensure_ascii=False) + '\n')
        f.close()


def main(page):
    url = 'http://bang.dangdang.com/books/fivestars/01.00.00.00.00.00-recent30-0-0-1-' + str(page)
    html = request_dandan(url)
    items = parse_result(html) # 解析过滤我们想要的信息
    for item in items:
        write_item_to_file(item)


if __name__ == "__main__":
    for i in range(1,26):
        main(i)

SRE实战互联网时代守护先锋，助力企业售后服务体系运筹帷幄！一键直达领取阿里云限量特价优惠。