|
|
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
下面是代码,跟着小甲鱼编的,已经添加header了,不知道为什么煎蛋还是把我禁了 难道要用代理??
请问怎么解决~??
- import urllib.request
- import os
- def url_open(url):
- req = urllib.request.Request(url)
- req.add_header(\'User-Agent\',\'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.125 Safari/537.36\')
- 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=\'OOXX\',pages=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(img_addrs)
- if __name__ == \'__main__\':
- download_mm()
复制代码
这是错误信息:
Traceback (most recent call last):
File \"C:/Python34/testpython/爬煎蛋的妹纸.py\", line 60, in <module>
download_mm()
File \"C:/Python34/testpython/爬煎蛋的妹纸.py\", line 51, in download_mm
page_num = int(get_page(url))
File \"C:/Python34/testpython/爬煎蛋的妹纸.py\", line 13, in get_page
html = url_open(url).decode(\'utf-8\')
File \"C:/Python34/testpython/爬煎蛋的妹纸.py\", line 7, in url_open
response = urllib.request.urlopen(url)
File \"C:\\Python34\\lib\\urllib\\request.py\", line 161, in urlopen
return opener.open(url, data, timeout)
File \"C:\\Python34\\lib\\urllib\\request.py\", line 469, in open
response = meth(req, response)
File \"C:\\Python34\\lib\\urllib\\request.py\", line 579, in http_response
\'http\', request, response, code, msg, hdrs)
File \"C:\\Python34\\lib\\urllib\\request.py\", line 507, in error
return self._call_chain(*args)
File \"C:\\Python34\\lib\\urllib\\request.py\", line 441, in _call_chain
result = func(*args)
File \"C:\\Python34\\lib\\urllib\\request.py\", line 587, in http_error_default
raise HTTPError(req.full_url, code, msg, hdrs, fp)
urllib.error.HTTPError: HTTP Error 403: Forbidden
来源: 刚学到爬虫XXOO,遇到403forbidden |
|