2、Python request、BeautifulSoup(download mm_pic)
import requests from bs4 import BeautifulSoup import os class DownLoadImg(object): def __init__(self): self.url = 'http://jandan.net/ooxx/' self.header = { 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.108 Safari/537.36'} def get_Page(self): response = self.open_url(self.url) page = response.text # print(page) soup = BeautifulSoup(page) page_c = soup.select('span.current-comment-page') # page_num = str(page_num).split('[')[-1].split(']')[0] page_num = page_c[0].next[1:-1] return page_num def open_url(self,url): response = requests.get(url,self.header) return response def get_and_save_Img(self): dir = os.path.exists('download_mm') if dir == False: os.mkdir('download_mm') os.chdir('download_mm') times = input('Please enter the number of pages to download:') i = 0 num = int(self.get_Page()) while i < int(times): url = self.url + 'page-' +str(num) print(url) response = self.open_url(url) html = response.text # print(html) bs = BeautifulSoup(html) img_list = bs.select('img') for img in img_list: src ='http:' + img.attrs['src'] img_name = str(src).split('/')[-1] get_img = requests.get(src, self.header) with open(img_name,'wb') as dl: dl.write(get_img.content) num -= 1 i += 1 if __name__ == "__main__": dl = DownLoadImg() dl.get_and_save_Img()