|
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
- import urllib.request
- import os
- import re
- import base64
- def url_open(url):
- # 添加文件头
- req = urllib.request.Request(url)
- req.add_header('User-Agent',
- 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.105 Safari/537.36')
- # 访问页面
- response = urllib.request.urlopen(req)
- html = response.read()
- return html
- # 获取页码
- def get_page(url):
- html = url_open(url).decode('utf-8')
- a = r'<span class="current-comment-page">\[(\d+)]'
- num = re.findall(a,html)
- return num[0]
- # 获取图片地址
- def find_imgs(url):
- html = url_open(url).decode('utf-8')
- a = r'<img src="([^"]+\.jpg)"'
- img_urls = re.findall(a,html)
- return img_urls
- # 保存图片
- def save_imgs(folder, img_addrs):
- for each in img_addrs:
- filename = each.split('/')[-1]
- with open(filename,'wb') as f:
- each_url = 'http:' + each
- img = url_open(each_url)
- f.write(img)
- def download_mm(folder='ooxx', pages=20):
- # 创建文件夹
- os.mkdir(folder)
- # 保存文件夹
- os.chdir(folder)
- url = 'http://jandan.net/ooxx/'
- # 获取页码
- page_num = int(get_page(url))
- for i in range(pages):
- page_num -= 1
- # 进行base64加密
- num = '20200901-' + str(page_num)
- bytes_num = num.encode('utf-8')
- str_num = base64.b64encode(bytes_num).decode('utf-8')
- # 获取下一页地址
- page_url = url + str_num + '#comments'
- # 获取页面内图片地址
- img_addrs = find_imgs(page_url)
- # 保存页面到指定的文件夹
- save_imgs(folder, img_addrs)
- # 完毕
- print("煎蛋网第%d页爬取完毕!" % page_num)
- print("结束退出!^_^")
- # 调用主函数
- if __name__ == '__main__':
- download_mm()
复制代码
主题:煎蛋网随手拍
方法:re正则表达式、os模块文件的函数、base64解加密
问题1:如何用xpath方法来摹写正则表达式的代码部分呢?
问题2:还可以再进行优化!
每次回帖奖励: 1鱼币, 奖励 10次, 每人最多可获得 1次, 中奖率 50% |
|