[已解决]Python零基础教学视屏第56讲，我按照视屏敲的代码，不知道哪里出错出了，实现不了

篱_灵

#代码如下
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/58.0.3029.110 Safari/537.36 Edge/16.16299')
    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)

    return img_addrs


def save_imgs(folder,img_addrs):
    for each in img_addrs:
        filename = each.split('/')[-1]
        with open(filename,'wb') as f:
            img = url_open(each)
            f.write(img)
   
def download_mm(folder='1',pages=10):
    os.mkdir(folder)
    os.chdir(folder)#切换为当前文件夹

    url='http://jandan.net/ooxx/'
    page_num = int(get_page(url))

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

if __name__  == '__main__':
    download_mm()




#报错如下
Traceback (most recent call last):
  File "D:\Program Installation\Python\Python36\小甲鱼\class56_download.py", line 60, in <module>
    download_mm()
  File "D:\Program Installation\Python\Python36\小甲鱼\class56_download.py", line 51, in download_mm
    page_num = int(get_page(url))
  File "D:\Program Installation\Python\Python36\小甲鱼\class56_download.py", line 14, in get_page
    html =  url_open(url).decode('utf-8')
  File "D:\Program Installation\Python\Python36\小甲鱼\class56_download.py", line 8, in url_open
    response = urllib.request.urlopen(url)
  File "D:\Program Installation\Python\Python36\lib\urllib\request.py", line 223, in urlopen
    return opener.open(url, data, timeout)
  File "D:\Program Installation\Python\Python36\lib\urllib\request.py", line 532, in open
    response = meth(req, response)
  File "D:\Program Installation\Python\Python36\lib\urllib\request.py", line 642, in http_response
    'http', request, response, code, msg, hdrs)
  File "D:\Program Installation\Python\Python36\lib\urllib\request.py", line 570, in error
    return self._call_chain(*args)
  File "D:\Program Installation\Python\Python36\lib\urllib\request.py", line 504, in _call_chain
    result = func(*args)
  File "D:\Program Installation\Python\Python36\lib\urllib\request.py", line 650, in http_error_default
    raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden

最佳答案

月排行榜 / 总排行榜

marlon

2018-5-24 09:42:52

https://baike.baidu.com/item/403%E9%94%99%E8%AF%AF/3686901?fr=aladdin
这个是被服务器拒绝了。爬的人太多了，服务器受不了

跳转到最佳答案楼层

BngThea

正常，更新了反爬机制，确实现在这样爬不了了

marlon

https://baike.baidu.com/item/403%E9%94%99%E8%AF%AF/3686901?fr=aladdin
这个是被服务器拒绝了。爬的人太多了，服务器受不了