def scan_proxy():
"""
扫描代理资源
:return:
"""
import requests
from pyquery import PyQuery as Pq
source_site = 'http://ip.qiaodm.com/'
header = {
'Host': 'ip.qiaodm.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36'
}
s = requests.session()
# 抓取页面
file_html = s.get(source_site).content
# 保存文件
# with open('test.html', 'a') as f:
# f.write(file_html.encode('utf-8'))
#
# # 读取抓取的页面
# with open('test.html', 'r') as f:
# file_html = f.read()
text_pq = Pq(file_html)
tr_list = text_pq('tbody').find('tr[style="text-align: center;"]')
print '单页共 %s 条记录' % len(tr_list)
for tr_item in tr_list:
# print Pq(tr_item).html()
# print('---------------------')
td_list = Pq(tr_item).find('td')
# print '单条共 %s 列字段' % len(td_list)
field_list = []
for td_item in Pq(td_list):
field = Pq(td_item).text()
field_list.append(field)
# print field
# print('++++++++++++++++++')
# 特殊处理ip地址
ip = Pq(td_list).eq(0).html()
# 去除干扰信息
ip = html.replace_html(ip, r'<p style="display:none;"/>')
ip = html.replace_html(ip, r'<p style="display: none;"/>')
ip = html.replace_html(ip, r'<p style=.*?display:.*?none;.*?>.*?</p>')
# 去除标签
ip = html.strip_html(ip)
# print ip
# 过滤掉非法ip地址
if len(ip.split('.')) != 4:
continue
# 特殊处理端口
port_key = Pq(td_list).eq(1).attr('class').split()[1]
if port_key not in PortDict:
print '发现新端口: %s' % port_key
continue
port = PortDict.get(port_key, '')
ProsyItem['Ip'] = ip.replace(' ', '')
ProsyItem['Port'] = port
ProsyItem['Type'] = field_list[2].strip()
ProsyItem['AnonymousDegree'] = field_list[3].strip()
ProsyItem['Area'] = field_list[4].strip()
ProsyItem['Speed'] = field_list[5].strip()
ProsyItem['ScanTime'] = field_list[6].strip()
# print ProsyItem
proxy_item = json.dumps(ProsyItem, ensure_ascii=False)
html.save_file('proxy.json', proxy_item + '\n', 'a')
def scan_proxy_qiaodm():
"""
扫描代理资源
:return:
"""
import requests
from pyquery import PyQuery as Pq
source_site = 'http://ip.qiaodm.com/'
header = {
'Host':
'ip.qiaodm.com',
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36'
}
s = requests.session()
# 抓取页面
file_html = s.get(source_site).content
# 保存文件
# with open('test.html', 'a') as f:
# f.write(file_html.encode('utf-8'))
#
# # 读取抓取的页面
# with open('test.html', 'r') as f:
# file_html = f.read()
text_pq = Pq(file_html)
tr_list = text_pq('tbody').find('tr[style="text-align: center;"]')
print '单页共 %s 条记录' % len(tr_list)
for tr_item in tr_list:
# print Pq(tr_item).html()
# print('---------------------')
td_list = Pq(tr_item).find('td')
# print '单条共 %s 列字段' % len(td_list)
field_list = []
for td_item in Pq(td_list):
field = Pq(td_item).text()
field_list.append(field)
# print field
# print('++++++++++++++++++')
# 特殊处理ip地址
ip = Pq(td_list).eq(0).html()
# 去除干扰信息
ip = html.replace_html(ip, r'<p style="display:none;"/>')
ip = html.replace_html(ip, r'<p style="display: none;"/>')
ip = html.replace_html(ip, r'<p style=.*?display:.*?none;.*?>.*?</p>')
# 去除标签
ip = html.strip_html(ip)
# print ip
# 过滤掉非法ip地址
if len(ip.split('.')) != 4:
continue
# 特殊处理端口
port_key = Pq(td_list).eq(1).attr('class').split()[1]
if port_key not in PortDict:
print '发现新端口: %s' % port_key
continue
port = PortDict.get(port_key, '')
ProsyItem['Ip'] = ip.replace(' ', '')
ProsyItem['Port'] = port
ProsyItem['Type'] = field_list[2].strip()
ProsyItem['AnonymousDegree'] = field_list[3].strip()
ProsyItem['Area'] = field_list[4].strip()
ProsyItem['Speed'] = field_list[5].strip()
ProsyItem['ScanTime'] = field_list[6].strip()
# print ProsyItem
proxy_item = json.dumps(ProsyItem, ensure_ascii=False)
html.save_file('proxy.json', proxy_item + '\n', 'a')
def clean(s):
return strip_html(s.strip('"')).strip()
