Examples are shown below:
__author__ = 'Fred Zhao' import requests from bs4 import BeautifulSoup import os from import urlretrieve class Picture(): def __init__(self): = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.95 Safari/537.36'} self.base_url = '/?cat=9987,653,655&page=' self.base_path = (__file__) def makedir(self, name): path = (self.base_path, name) isExist = (path) if not isExist: (path) print("File has been created.") else: print('OK!The file is existed. You do not need create a new one.') (path) def request(self, url): r = (url, headers=) return r def get_img(self, page): r = (self.base_url + str(page)) plist = BeautifulSoup(, 'lxml').find('div', id='plist') item = plist.find_all('li', class_='gl-item') print(len(item)) ('pictures') num = 0 for i in item: num += 1 imglist = ('div', class_='p-img') print(num) img = ('img') print('This is %s picture' %num) if ('src'): url = 'https:' + ('src') fileName = ('src').split('/')[-1] urlretrieve(url, filename=fileName) elif ('data-lazy-img'): url = 'https:' + ('data-lazy-img') fileName = ('data-lazy-img').split('/')[-1] urlretrieve(url, filename=fileName) if __name__ == '__main__': picture = Picture() for i in range(2): # Control the number of pages crawled picture.get_img(i+1)
Above this Python crawler to achieve crawling Jingdong cell phone page images (example code) is all I have shared with you, I hope to be able to give you a reference, and I hope you will support me more.