[已解决]python爬取妹子图出现问题

°蓝鲤歌蓝 · 发表于 2017-12-5 22:31:05

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

按照教程来的，求大佬帮忙。
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) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0")
response = urllib.request.urlopen(req)
html = response.read()
#print(url)
return html

def get_page(url):
html = url_open(url).decode('utf-8')

a = html.find('current-comment-page') + len('current-comment-page">[')
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(folder,img_addrs)

if __name__ == '__main__':
download_mm()

最佳答案

月排行榜 / 总排行榜

有牵挂才会怕

2017-12-5 22:58:41

这个我以前也碰到过，因为小甲鱼出的视频和现在比比较早了，当时我记得有鱼油说是煎蛋网的图片已经经过了加密，所以爬不了了

这个是我的错误反馈：
Traceback (most recent call last):
File "F:\python保存\ooxx.py", line 61, in <module>
download_mm()
File "F:\python保存\ooxx.py", line 52, in download_mm
page_num = int(get_page(url))
ValueError: invalid literal for int() with base 10: '>\r\n\t<head>\r\n\t\t<meta charset="UTF-8">\r\n\t\t<title>页面丢失了</title>\r\n\t\t<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no, minimum-scale=1.0, maximum-scale
>>>

跳转到最佳答案楼层

°蓝鲤歌蓝 · 发表于 2017-12-5 22:39:05

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) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0")
response = urllib.request.urlopen(req)
html = response.read()
#print(url)
return html
def get_page(url):
html = url_open(url).decode('utf-8')
a = html.find('current-comment-page') + len('current-comment-page">[')
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: #从这开始错误
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(folder,img_addrs)
if __name__ == '__main__':
download_mm()
'''

复制代码

有牵挂才会怕 · 发表于 2017-12-5 22:58:41

这个我以前也碰到过，因为小甲鱼出的视频和现在比比较早了，当时我记得有鱼油说是煎蛋网的图片已经经过了加密，所以爬不了了

这个是我的错误反馈：
Traceback (most recent call last):
File "F:\python保存\ooxx.py", line 61, in <module>
download_mm()
File "F:\python保存\ooxx.py", line 52, in download_mm
page_num = int(get_page(url))
ValueError: invalid literal for int() with base 10: '>\r\n\t<head>\r\n\t\t<meta charset="UTF-8">\r\n\t\t<title>页面丢失了</title>\r\n\t\t<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=no, minimum-scale=1.0, maximum-scale
>>>

°蓝鲤歌蓝 · 发表于 2017-12-5 23:32:20

有牵挂才会怕发表于 2017-12-5 22:58
这个我以前也碰到过，因为小甲鱼出的视频和现在比比较早了，当时我记得有鱼油说是煎蛋网的图片已经经过了加 ...

我知道哪里出问题了，已经解决了。不过虽然没有报错，文件里却没有任何图片，可能是加密了吧，可惜了。

账号		自动登录	找回密码
密码			立即注册

[已解决]python爬取妹子图出现问题

马上注册，结交更多好友，享用更多功能^_^

RE: python爬取妹子图出现问题

浏览过的版块