什么都不说,直接上代码(目标是爬豆瓣新书)
import requests
import parsel
def get_biao_qian():
url = 'https://market.douban.com/book/?utm_campaign=book_nav_freyr&utm_source=douban&utm_medium=pc_web'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36'
}
request = requests.get(url, headers=headers).text
return request
def book_item(html):
sele = parsel.Selector(html)
href_url = sele.css('.book-list li a::attr(href)').getall()
text = sele.css('.panel-detail h3::text').getall()
panel = sele.css('.panel-detail span i::text').getall()
for a_1, b_1, c_1 in zip(href_url, text, panel):
print(f'链接:{a_1}\n书名:{b_1}\t\t价格:{c_1}元')
if __name__ == '__main__':
ht = get_biao_qian()
book_item(ht)