白泽、 发表于 2022-3-4 20:40:04

求助 这是怎么回事啊，怎么解决

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/98.0.4758.102 Safari/537.36 Edg/98.0.1108.62')
    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

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)
      else:
            b = a + 9

      a = html.find('img src=',b)
    return img_addrs

def save_imgs(folder,img_addrs):
    for each in img_addrs:
      filename = each.split('/')[-1]
      with open(folder,'wb') as f:
            img = url_open(each)
            f.write(img)

def download_mm(folder='OOXX',pages=10):
   
    os.mkdir(folder)
    os.chdir(folder)

    url ='http://jiandan.net/girl/'
    page_num = int(get_page(url))

    for i in range(pages):
      page_num -= i
      page_url = url+str(page_num)+'#commen'
      img_addrs = find_imgs(page_url)
      save_imgs(folder,img_addrs)

if __name__ == '__main__':
    download_mm()

isdkz 发表于 2022-3-4 20:42:50

占楼

isdkz 发表于 2022-3-4 20:53:20

本帖最后由 isdkz 于 2022-3-4 21:01 编辑


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/98.0.4758.102 Safari/537.36 Edg/98.0.1108.62')
    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

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)
      else:
            b = a + 9

      a = html.find('img src=',b)
    return img_addrs

def save_imgs(folder,img_addrs):
    for each in img_addrs:
      print(each)
      filename = each.split('/')[-1]
      with open(filename,'wb') as f:         # 这里改成 filename

            img = url_open("http:" + each)   # 这里加个 http:
            f.write(img)

def download_mm(folder='OOXX',pages=10):
    if not os.path.exists(folder):               # 这里先判断一下指定的文件夹是否存在，不存在再新建
      os.mkdir(folder)
    os.chdir(folder)

    url ='http://jiandan.net/girl/'
    page_num = int(get_page(url))

    for i in range(pages):
      page_num -= i
      page_url = url+str(page_num)+'#commen'
      img_addrs = find_imgs(page_url)
      save_imgs(folder, img_addrs)      

if __name__ == '__main__':
    download_mm()

白泽、 发表于 2022-3-4 21:23:20

isdkz 发表于 2022-3-4 20:53


谢谢大佬！！！
页: [1]
查看完整版本: 求助 这是怎么回事啊，怎么解决