Python实战 | 爬取当当网 TOP500 畅销书

目标网页：当当网书籍畅销榜 http://bang.dangdang.com/books/bestsellers/01.00.00.00.00.00-24hours-0-0-1-1

爬取结果：

代码：

import requests,re,json
 
def request_dangdang(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">&yen;(.*?)</span>.*?</li>',re.S)
    items = re.findall(pattern,html)
    for item in items:
        yield{                #写入为字典类型
            'range':item[0],
            'iamge':item[1],
            'title':item[2],
            'recommend':item[3],
            'author':item[4],
            'times':item[5],
            'price':item[6]
        }
    print(1)
    for item in items:
        print(item)
 
def write_item_to_file(item):
    #print("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') #将字典类型转化为字符串写入文件
        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_dangdang(url)
    items = parse_result(html)  #解析过滤想要的信息
    for item in items:
        write_item_to_file(item)
 
if __name__ == "__main__":
    for i in range(1,26):
        main(i)

参考网址：https://blog.csdn.net/weixin_42469142/article/details/89856325