|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
如题,按照小甲鱼老师课程所写的代码,现在只能爬到某页面中的一张广告图片,其他图片都爬不到,求教大神。。
- import urllib.request
- import os
- def url_open(url):
- req = urllib.request.Request(url)
- req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/64.0.3282.140 Safari/537.36 Edge/17.17134')
- response = urllib.request.urlopen(url)
- html = response.read()
- return html
- def get_page(url):
- html = url_open(url).decode('utf-8')
- a = html.find('current-comment-page') + 23
- b = html.find(']',a)
- return html[a:b]
- def find_imgs(url):
- html = url_open(url).decode('utf-8')
- img_addrs = []
- a = html.find('img src=')
- while a!= -1:
- b = html.find('.jpg',a, a+255)
- if b != -1:
- img_addrs.append(html[a+9:b+4])
- else:
- b = a + 9
- a = html.find('img src=',b)
- for each in img_addrs:
- print(each)
- return img_addrs
- def save_imgs(floder,img_addrs):
- for each in img_addrs:
- filename = each.split('/')[-1]
- with open(filename,'wb') as f:
- try:
- img = url_open(each)
- f.write(img)
- except:
- continue
- def pachong(folder='mm',pages=10):
- try:
- os.chdir(folder)
- except:
- os.mkdir(folder)
- os.chdir(folder)
- url = 'http://jandan.net/ooxx/'
- page_num = int(get_page(url))
- for i in range(pages):
- page_num -= 1
- page_url = url + 'page-' + str(page_num) + '#comments'
- img_addrs = find_imgs(page_url)
- save_imgs(folder,img_addrs)
- if __name__ == '__main__':
- pachong()
复制代码
|
|