|
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
Traceback (most recent call last):
File "E:\练习题\4.16\抓图\抓图.py", line 54, in <module>
download_mm()
File "E:\练习题\4.16\抓图\抓图.py", line 45, in download_mm
page_num = int(get_page(url))
File "E:\练习题\4.16\抓图\抓图.py", line 14, in get_page
html = url_open(url).decode('utf-8')
File "E:\练习题\4.16\抓图\抓图.py", line 8, in url_open
response = urllib.request.urlopen(url)
File "F:\lib\urllib\request.py", line 223, in urlopen
return opener.open(url, data, timeout)
File "F:\lib\urllib\request.py", line 532, in open
response = meth(req, response)
File "F:\lib\urllib\request.py", line 642, in http_response
'http', request, response, code, msg, hdrs)
File "F:\lib\urllib\request.py", line 570, in error
return self._call_chain(*args)
File "F:\lib\urllib\request.py", line 504, in _call_chain
result = func(*args)
File "F:\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
以上是错误
一下是所有程序
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; WOW64; rv:56.0) Gecko/20100101 Firefox/56.0')
#模拟人访问隐藏软件访问
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') + 10
b = html.find(']',a)#从a里找从‘]’结束
return html[a:b]
# print(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 im_addrs:
filename = each.split('/')[-1]#从最后一个/号分开
with open(filename,'wb') as f:
img = url_open(each)
f.write(img)
'''
def download_mm(folder='heihei',papges=10):
os.mkdir (folder)
os.chdir (folder)
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()
如果一个ip频繁访问,会被封的。一般等12或者24小时会自动解封。
|
|