Python实现【亚马逊商品】数据采集

headers = {
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
'Accept-Encoding': 'gzip, deflate, br',
'Accept-Language': 'zh-CN,zh;q=0.9',
'Cache-Control': 'max-age=0',
'Connection': 'keep-alive',
'Cookie': 'session-id=460-4132650-8765807; i18n-prefs=CNY; ubid-acbcn=457-7935785-7667244; session-token=Laa3G6hMbBpdAIPYwutQqKxkSISU8fb2jTr0JiczqkeVISvqn2eqjw4N0BAbYfmy8+/S1B3kLvDb9ImsBnbwQHU6JG8EToefDoi69keaL1F6ExYDXCSqFF0hC4fkGAFJlNYYNqfVlvj5ewTVJP1pYgL4JG2tjM5O2Uk7ufiL9s7gvidAMaUj1QtBW5puqmoG; csm-hit=adb:adblk_no&t:1645531896484&tb:s-VMQ97YXPSC1MBACTN14J|1645531895768; session-id-time=2082729601l',
'downlink': '10',
'ect': '4g',
'Host': 'www.amazon.cn',
'Referer': 'https://www.amazon.cn/b/ref=s9_acss_bw_cg_pccateg_2a1_w?node=106200071&pf_rd_m=A1U5RCOVU0NYF2&pf_rd_s=merchandised-search-2&pf_rd_r=KE929JDVF8QRWWDQCWC0&pf_rd_t=101&pf_rd_p=cdcd9a0d-d7cf-4dab-80db-2b7d63266973&pf_rd_i=42689071',
'rtt': '150',
'sec-ch-ua': '" Not A;Brand";v="99", "Chromium";v="98", "Google Chrome";v="98"',
'sec-ch-ua-mobile': '?0',
'sec-ch-ua-platform': '"Windows"',
'Sec-Fetch-Dest': 'document',
'Sec-Fetch-Mode': 'navigate',
'Sec-Fetch-Site': 'same-origin',
'Sec-Fetch-User': '?1',
'Upgrade-Insecure-Requests': '1',
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36',
}
url = 'https://www.amazon.cn/s?rh=n%3A106200071&fs=true&ref=lp_106200071_sar'
response = requests.get(url=url, headers=headers)

print(response)

data_html = response.text

selector = parsel.Selector(data_html)
divs = selector.css('.a-section.a-spacing-base')
for div in divs:
# ::text: 提取到标签文本内容
title = div.css('.a-size-base-plus.a-color-base.a-text-normal::text').get()
price = div.css('.a-size-base.a-link-normal.s-underline-text.s-underline-link-text.s-link-style.a-text-normal .a-price .a-offscreen::text').get()
img_url = div.css('.a-section.aok-relative.s-image-square-aspect .s-image::attr(src)').get()
link = div.css('.a-link-normal.s-no-outline::attr(href)').get()
print(title, price, img_url, link)

with open('亚马逊.csv', mode='a', encoding='utf-8', newline='') as f:
csv_writer = csv.writer(f)
csv_writer.writerow([title, price, img_url, link])

for page in range(1, 401):
url = f'https://www.amazon.cn/s?i=computers&rh=n%3A106200071&fs=true&page={page}&qid=1645537294&ref=sr_pg_3'