2024年Python最新Python爬虫入门教程27：爬取某电商平台数据内容并做数据可视化_爬取淘宝商品数据python

‘详情页’])

csv_writer.writeheader()

for page in range(1, 26):

print(f’正在保存第{page}页数据内容===========')

url = f’http://bang.dangdang.com/books/bestsellers/01.00.00.00.00.00-year-2017-0-1-{page}’

headers = {

‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.90 Safari/537.36’

}

response = requests.get(url=url, headers=headers)

print(response.text)

selector = parsel.Selector(response.text)

lis = selector.css(‘.bang_list_mode li’)

for li in lis:

title = li.css(‘.name a::attr(title)’).get() # 标题/书名

recommend = li.css(‘.tuijian::text’).get() # 推荐

star = li.css(‘.star a::text’).get() # 评价

author = li.css(‘div:nth-child(5) a:nth-child(1)::attr(title)’).get() # 作者

date = li.css(‘div:nth-child(6) span::text’).get() # 出版日期

press = li.css(‘div:nth-child(6) a::text’).get() # 出版社

price_r = li.css(‘.price .price_r::text’).get() # 原价

price_n = li.css(‘.price .price_n::text’).get() # 售价

price_e = li.css(‘.price_e span::text’).get() # 电子书价格

href = li.css(‘.name a::attr(href)’).get() # 详情页

dit = {

‘标题’: title,

‘推荐’: recommend,

‘评价’: star,

‘作者’: author,

‘出版日期’: date,

‘出版社’: press,

‘原价’: price_r,

‘售价’: price_n,

‘电子书价格’: price_e,

‘详情页’: href,