Python爬取图片项目介绍

第三方库：requests,fake_useragent(产生随机请求头进行访问)

代码实现：

import requests

from fake_useragent import UserAgent

filename=0

class photo_spider(object):

def __init__(self):

self.url = ‘https://api.500px.com/v1/photos?rpp=50&feature=popular&image_size%5B%5D=1&image_size%5B%5D=2&image_size%5B%5D=32&image_size%5B%5D=31&image_size%5B%5D=33&image_size%5B%5D=34&image_size%5B%5D=35&image_size%5B%5D=36&image_size%5B%5D=2048&image_size%5B%5D=4&image_size%5B%5D=14&sort=&include_states=true&include_licensing=true&formats=jpeg%2Clytro&only=&exclude=&personalized_categories=&page={}&rpp=50’

ua = UserAgent(verify_ssl=False)

# 产生随机的UserAgent请求头进行访问。

for i in range(1, 100):

self.headers = {

‘User-Agent’: ua.random

}

#发送请求，获取网页。

def get_html(self,url):

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

html = response.json()

return html

#获取图片链接地址，保存图片格式到本地文件夹。

def get_imageUrl(self,html):

global filename

content_list=html[‘photos’]

for content in content_list:

image_url = content[‘image_url’]

# print(image_url[8])

imageUrl = image_url[8]

r = requests.get(imageUrl, headers=self.headers)

with open(‘D:/pycharm文件/photo/’ + str(filename) + ‘.jpg’, ‘wb’) as f:

f.write(r.content)

filename += 1

#获取多页及函数调用

def main(self):

start = int(input(‘输入开始：’))

end = int(input(‘输入结束页：’))

for page in range(start, end + 1):

print(‘第%s页’ % page)

url = self.url.format(page)

html = self.get_html(url)

self.get_imageUrl(html)

if __name__ == ‘__main__’:

spider = photo_spider()

spider.main()