import json
import re
from utils import get_page
from pyquery import PyQuery as pq

# 元類
class ProxyMetaclass(type):
 def __new__(cls, name, bases, attrs):
  count = 0
  attrs['__CrawlFunc__'] = []
  for k, v in attrs.items():
   if 'crawl_' in k:
    attrs['__CrawlFunc__'].append(k)
    count += 1
  attrs['__CrawlFuncCount__'] = count
  return type.__new__(cls, name, bases, attrs)

class Crawler(object, metaclass=ProxyMetaclass):
 def get_proxies(self, callback):
  proxies = []
  for proxy in eval("self.{}()".format(callback)):
   print('成功獲取到代理', proxy)
   proxies.append(proxy)
  return proxies

 def crawl_daili66(self, page_count=4):
  start_url = 'http://www.66ip.cn/{}.html'
  urls = [start_url.format(page) for page in range(1, page_count + 1)]
  for url in urls:
   print('Crawling', url)
   html = get_page(url)
   if html:
    doc = pq(html)
    trs = doc('.containerbox table tr:gt(0)').items()
    for tr in trs:
     ip = tr.find('td:nth-child(1)').text()
     port = tr.find('td:nth-child(2)').text()
     yield ':'.join([ip, port])

 def crawl_xicidaili(self):
  for i in range(1, 3):
   start_url = 'http://www.xicidaili.com/nn/{}'.format(i)
   headers = {
    'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Host':'www.xicidaili.com',
    'Referer':'http://www.xicidaili.com/nn/3',
    'Upgrade-Insecure-Requests':'1',
   }
   html = get_page(start_url, options=headers)
   if html:
    find_trs = re.compile('<tr class.*?>(.*?)</tr>', re.S)
    trs = find_trs.findall(html)
    for tr in trs:
     find_ip = re.compile('<td>(\d+\.\d+\.\d+\.\d+)</td>') 
     re_ip_address = find_ip.findall(tr)
     find_port = re.compile('<td>(\d+)</td>')
     re_port = find_port.findall(tr)
     for address,port in zip(re_ip_address, re_port):
      address_port = address+':'+port
      yield address_port.replace(' ','')

 def crawl_ip3366(self):
  for i in range(1, 4):
   start_url = 'http://www.ip3366.net/?stype=1&page={}'.format(i)
   html = get_page(start_url)
   if html:
    find_tr = re.compile('<tr>(.*?)</tr>', re.S)
    trs = find_tr.findall(html)
    for s in range(1, len(trs)):
     find_ip = re.compile('<td>(\d+\.\d+\.\d+\.\d+)</td>')
     re_ip_address = find_ip.findall(trs[s])
     find_port = re.compile('<td>(\d+)</td>')
     re_port = find_port.findall(trs[s])
     for address,port in zip(re_ip_address, re_port):
      address_port = address+':'+port
      yield address_port.replace(' ','')

 def crawl_kuaidaili(self):
  for i in range(1, 4):
   start_url = 'http://www.kuaidaili.com/free/inha/{}/'.format(i)
   html = get_page(start_url)
   if html:
    ip_address = re.compile('<td data-title="IP">(.*?)</td>') 
    re_ip_address = ip_address.findall(html)
    port = re.compile('<td data-title="PORT">(.*?)</td>')
    re_port = port.findall(html)
    for address,port in zip(re_ip_address, re_port):
     address_port = address+':'+port
     yield address_port.replace(' ','')

import requests
from requests.exceptions import ConnectionError

base_headers = {
 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/77.0.3865.120 Safari/537.36',
 'Accept-Encoding': 'gzip, deflate, sdch',
 'Accept-Language': 'en-US,en;q=0.9,zh-CN;q=0.8,zh;q=0.7'
}

def get_page(url, options={}):

 headers = dict(base_headers, **options)
 print('正在抓取', url)
 try:
  response = requests.get(url, headers=headers)
  print('抓取成功', url, response.status_code)
  if response.status_code == 200:
   return response.text
 except ConnectionError:
  print('抓取失敗', url)
  return None

from crawler import Crawler
from setting import *
import sys

class Getter():
 def __init__(self):
  self.crawler = Crawler()
 
 def run(self):
  print('獲取器開(kāi)始執(zhí)行')
  for callback_label in range(self.crawler.__CrawlFuncCount__):
   callback = self.crawler.__CrawlFunc__[callback_label]
   # 獲取代理
   all_ip = self.crawler.get_proxies(callback)

if __name__ == '__main__':
 get = Getter()
 get.run()