qqqq79852852
发表于 2015-9-29 08:03:23
厉害 啊,来学习
小榆萍
发表于 2015-9-30 11:07:15
就怕流氓有文化
xaltin
发表于 2015-10-1 11:12:31
点亮star在哪里?先点个赞
chuxue
发表于 2015-10-5 17:56:36
lihais dfjado
classic64g
发表于 2015-10-5 20:24:09
学习
航海王
发表于 2015-10-6 07:24:04
看看
wking
发表于 2015-10-7 15:40:03
学习学习
不坏不修
发表于 2015-10-10 16:57:34
可能吗
jxj21
发表于 2015-10-16 10:36:06
如何爬
hongzhong
发表于 2015-10-16 14:48:00
git是什么
NewSong
发表于 2015-10-16 18:18:26
谢谢
嗯333
发表于 2015-10-17 23:10:33
66666
Prince8
发表于 2015-10-18 12:12:11
66666666666:lol:
qqqq79852852
发表于 2015-10-18 12:56:30
支持一下!
manny
发表于 2015-10-19 10:33:27
两包烟的钱,把不了妹买不了田,不如拿来支持小甲鱼推出更多原创教学视频!
ianv
发表于 2015-10-19 11:45:12
import urllib.request
import urllib.error
import os
import sys
import http.server
import http.client
import time
import re
import random
import math
data = None
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/31.0.1650.63 Safari/537.36'}
enctype = 'utf-8'
proxies = []
max_error_times = 5 #最多允许失败5次,否则放弃该图片下载
def create_localhost():
number = int((math.sqrt(5)-1)/2) * len(proxies)
for x in range(number):
proxies.append(None)
def get_result(req_or_url,is_retrieve=False,filename = None): #flag是否使用retrieve
error_time = 0
while True:
try:
if error_time == max_error_times:
print('失败次数达%d次......放弃操作' % max_error_times)
return None
error_time += 1
if is_retrieve:
return urllib.request.urlretrieve(req_or_url,filename)
else:
return urllib.request.urlopen(req_or_url)
except urllib.error.URLError as e:
if hasattr(e,'code'):
print(e.code,e.reason)
change_proxy()
continue
elif hasattr(e,'reason'):
print(e)
change_proxy()
continue
except (ConnectionResetError,http.client.BadStatusLine) as e:
print(e)
change_proxy()
continue
except TimeoutError as e:
print(e)
print('服务器长时间无响应,自动切换代理.....')
change_proxy()
continue
def get_proxy():
global data,headers,proxies
req = urllib.request.Request('http://www.xici.net.co',None,headers)
response = get_result(req)
html = response.read().decode('utf-8')
p = re.compile(r'''<tr\sclass[^>]*>\s+
<td>.+</td>\s+
<td>(.*)?</td>\s+
<td>(.*)?</td>\s+
<td>(.*)?</td>\s+
<td>(.*)?</td>\s+
<td>(.*)?</td>\s+
<td>(.*)?</td>\s+
</tr>''',re.VERBOSE)
proxy_list = p.findall(html)
for each_proxy in proxy_list:
if each_proxy == 'HTTP':
proxies.append(each_proxy+':'+each_proxy)
def change_proxy():
proxy = random.choice(proxies)
if proxy == None:
proxy_support = proxy_support = urllib.request.ProxyHandler({})
else:
proxy_support = urllib.request.ProxyHandler({'http':proxy})
opener = urllib.request.build_opener(proxy_support)
opener.addheaders = [('User-Agent',headers['User-Agent'])]
urllib.request.install_opener(opener)
print('智能切换代理:%s' % ('本机' if proxy==None else proxy))
def get_page(): #获取最大页数
home = 'http://jandan.net/ooxx'
global data,headers,enctype
req = urllib.request.Request(home,data,headers)
response = get_result(req)
html = response.read().decode(enctype)
find_string = 'current-comment-page'
find_start = html.index(find_string) + len(find_string) + 3
find_end = html.index(']',find_start+1)
return int(html)
test = None
def get_pic(page): #生成器,返回一个图片链接
global data,headers,enctype
while True:
url = 'http://jandan.net/ooxx/page-%d' % page
print('当前页面:%d' % page)
req = urllib.request.Request(url,data,headers)
response = get_result(req)
if response == None:
print('获取页面失败.....')
sys.exit()
html = response.read().decode(enctype)
pic = re.compile(r'<img\s+src="(http://.+?\.(?:jpg|jpeg|gif))"')
for pic in pic.finditer(html):
yield pic.group(1)
time.sleep(5)
page -= 1
if page<1:
break
save_path = 'D:\\图片\\妹子图'
def download():
count = 1
global data,headers
for pic_url in get_pic(get_page()): #get_page()改为页数如1000可从1000页开始下载
file_name = os.path.split(pic_url)
if not os.path.isdir(save_path): #目录不存在就创建
os.makedirs(save_path)
get_result(pic_url,True,save_path+'\\'+file_name)
print('本次成功下载第%d个图片! %s' % (count , pic_url))
count += 1
if __name__ == '__main__':
get_proxy()
create_localhost()
download()
Anson.zeng
发表于 2015-10-20 08:27:50
看看,,,,,,
ipenny
发表于 2015-10-22 17:53:02
收点儿鱼币不过分吧
lyman2501
发表于 2015-10-26 16:09:11
{:5_92:}
五道杠
发表于 2015-10-27 12:49:33
看看
页:
1
2
3
[4]
5
6
7
8
9
10
11
12
13