|
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
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/59.0.3071.86 Safari/537.36')
response = urllib.request.urlopen(url)
html = response.read()
print(url)
return html
def get_page(url):
html =url_open(url).decode('utf-8')
print(html)
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')
print(html)
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)
print(img_addrs)
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=5):
os.mkdir(folder)
os.chdir(folder)
url = "https://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()
用你的代码我发现了如下几处错误与不妥
1.之所以出现上面的错误是因为,你在save_imgs的时候,请求的图片的url不对
- //wx2.sinaimg.cn/large/7ecfe92dly1fkk90rp9bmg20ez0bqu12.gif
复制代码
这种url放到浏览器里是可以访问的,因为默认使用了http协议,但是在python里面就需要手动添加http协议
- with open(os.path.join(folder,filename),'wb') as f:
- img = url_open('http:'+each)
复制代码
2.还有逻辑错误
- url = "https://jandan.net/ooxx/"
- page_num= int(get_page(url))
- for i in range(pages):
- page_num += i
复制代码
这段代码你是想,获得当前页面的page数目,然后增加page数,从而获得新的页面
只是,好好观察页面的话,会发现https://jandan.net/ooxx/这个url所访问的是page=201的页面,但是201是最后一个页面,从1-201,访问202的话,是没有的
3. - os.mkdir(folder)
- os.chdir(folder)
复制代码
新建文件夹,然后改变当前路径
如果文件夹存在的话,会报错,所以每次都需要删除文件夹,然后再尝试
推荐
- if not os.path.exists(folder):
- os.makedirs(folder)
复制代码- with open(os.path.join(folder,filename),'wb') as f:
- img = url_open('http:'+each)
复制代码
4.还有就是推荐将https修改为http进行访问
下面是我修改后的
- 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/59.0.3071.86 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(os.path.join(folder,filename),'wb') as f:
- img = url_open('http:'+each)
- print('http:'+each)
- f.write(img)
-
-
- def download_mm(folder='ooxx',pages=5):
- if not os.path.exists(folder):
- os.makedirs(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()
复制代码
|
-
|