Python爬虫入门教程10：彼岸壁纸爬取

“”“获取网页数据”“”

headers = {

‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36’

}

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

return response

获取每张壁纸的ID💦

def main(html_url):

“”“获取图片ID”“”

response = get_response(html_url)

selector = parsel.Selector(response.text)

image_info = selector.css(‘.list ul li’)

for link in image_info:

image_title = link.css(‘a::attr(title)’).get()

进行简单的判断，如果有标题就获取ID

if image_title:

id_info = link.css(‘a::attr(href)’).get()

/desk/23177.htm

image_id = id_info.replace(‘.htm’, ‘’).split(‘/’)[-1]

获取每张壁纸的