|
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
#写于学习Python教程P57之后,未使用正则表达式
##网址:http://jandan.net/ooxx
##代码未考虑非jpg格式图片,已知网站还有gif格式图片,有待改进
- import urllib.request
- import os
- def open_url(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/80.0.3987.116 Safari/537.36')
- response = urllib.request.urlopen(url)
- html = response.read()
- return html
- def find_imgs(url):
- html = open_url(url).decode('utf-8')
- pic_list = []
- a = html.find('查看原图')
- while a!=-1:
- c = a + 4
- a = a - 127
- b = html.find('.jpg', a) + 4
- pic_list.append('https://' + html[a:b])
- a = html.find('查看原图', c)
- return pic_list
- def get_next_page(url):
- html = open_url(url).decode('utf-8')
- a = html.find('下一页') - 80
- a = html.find('//', a)
- b = html.find('comments', a)
- return 'https:' + html[a:b] + 'comments'
- def sava_imgs(folder, pic_list):
- for each in pic_list:
- filename = each.split('/')[-1]
- with open(filename,'wb') as f:
- img = open_url(each)
- f.write(img)
- def g_pic_dl(folder='妹子图',pages=10):
- pic_list = []
- url = "http://jandan.net/ooxx"
- os.mkdir(folder)
- os.chdir(folder)
- while pages > 0:
- pic_list=find_imgs(url)
- sava_imgs(folder, pic_list)
- url = get_next_page(url)
- if __name__ == '__main__':
- g_pic_dl()
复制代码 |
|