#要爬取的url
url_l = []
#请求头
MY_USER_AGENT = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; AcooBrowser; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0; Acoo Browser; SLCC1; .NET CLR 2.0.50727; Media Center PC 5.0; .NET CLR 3.0.04506)",
"Mozilla/4.0 (compatible; MSIE 7.0; AOL 9.5; AOLBuild 4337.35; Windows NT 5.1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows; U; MSIE 9.0; Windows NT 9.0; en-US)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 2.0.50727; Media Center PC 6.0)",
"Mozilla/5.0 (compatible; MSIE 8.0; Windows NT 6.0; Trident/4.0; WOW64; Trident/4.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; .NET CLR 1.0.3705; .NET CLR 1.1.4322)",
"Mozilla/4.0 (compatible; MSIE 7.0b; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.2; .NET CLR 3.0.04506.30)",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN) AppleWebKit/523.15 (KHTML, like Gecko, Safari/419.3) Arora/0.3 (Change: 287 c9dfb30)",
"Mozilla/5.0 (X11; U; Linux; en-US) AppleWebKit/527+ (KHTML, like Gecko, Safari/419.3) Arora/0.6",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.2pre) Gecko/20070215 K-Ninja/2.1.1",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/20080705 Firefox/3.0 Kapiko/3.0",
"Mozilla/5.0 (X11; Linux i686; U;) Gecko/20070322 Kazehakase/0.4.5",
"Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.8) Gecko Fedora/1.9.0.8-1.fc10 Kazehakase/0.5.6",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; fr) Presto/2.9.168 Version/11.52",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
"Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36",
]
Android_USER_AGENT = [
'Mozilla/5.0 (Linux; Android 7.1.1; MI 6 Build/NMF26X; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/57.0.2987.132 MQQBrowser/6.2 TBS/043807 Mobile Safari/537.36 MicroMessenger/6.6.1.1220(0x26060135) NetType/WIFI Language/zh_CN',
'Mozilla/5.0 (Linux; Android 7.1.1; OD103 Build/NMF26F; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/53.0.2785.49 Mobile MQQBrowser/6.2 TBS/043632 Safari/537.36 MicroMessenger/6.6.1.1220(0x26060135) NetType/4G Language/zh_CN',
'Mozilla/5.0 (Linux; Android 6.0.1; SM919 Build/MXB48T; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/53.0.2785.49 Mobile MQQBrowser/6.2 TBS/043632 Safari/537.36 MicroMessenger/6.6.1.1220(0x26060135) NetType/WIFI Language/zh_CN',
'Mozilla/5.0 (Linux; Android 5.1.1; vivo X6S A Build/LMY47V; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/53.0.2785.49 Mobile MQQBrowser/6.2 TBS/043632 Safari/537.36 MicroMessenger/6.6.1.1220(0x26060135) NetType/WIFI Language/zh_CN',
'Mozilla/5.0 (Linux; Android 5.1; HUAWEI TAG-AL00 Build/HUAWEITAG-AL00; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/53.0.2785.49 Mobile MQQBrowser/6.2 TBS/043622 Safari/537.36 MicroMessenger/6.6.1.1220(0x26060135) NetType/4G Language/zh_CN',
'Mozilla/5.0 (Linux; Android 7.0; FRD-AL10 Build/HUAWEIFRD-AL10; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/62.0.3202.84 Mobile Safari/537.36 MicroMessenger/6.7.3.1360(0x26070336) NetType/WIFI Language/zh_CN Process/appbrand0'
]
iPhone_USER_AGENT = [
'Mozilla/5.0 (iPhone; CPU iPhone OS 9_3_2 like Mac OS X) AppleWebKit/601.1.46 (KHTML, like Gecko) Mobile/13F69 MicroMessenger/6.6.1 NetType/4G Language/zh_CN',
'Mozilla/5.0 (iPhone; CPU iPhone OS 11_2_2 like Mac OS X) AppleWebKit/604.4.7 (KHTML, like Gecko) Mobile/15C202 MicroMessenger/6.6.1 NetType/4G Language/zh_CN',
'Mozilla/5.0 (iPhone; CPU iPhone OS 11_1_1 like Mac OS X) AppleWebKit/604.3.5 (KHTML, like Gecko) Mobile/15B150 MicroMessenger/6.6.1 NetType/WIFI Language/zh_CN',
'Mozilla/5.0 (iphone x Build/MXB48T; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/53.0.2785.49 Mobile MQQBrowser/6.2 TBS/043632 Safari/537.36 MicroMessenger/6.6.1.1220(0x26060135) NetType/WIFI Language/zh_CN'
]
import random
import multiprocessing.managers
from multiprocessing import Queue
task_queue = Queue()
result_queue = Queue()
import requests
from bs4 import BeautifulSoup
import multiprocessing
success_num = 0
CONSTANT = 0
#获取代理
def getProxyIp():
global CONSTANT
proxy = []
for i in range(1, 15):
print(i)
header = {'User-Agent': random.choice(random.choice([MY_USER_AGENT, iPhone_USER_AGENT, Android_USER_AGENT]))}
r = requests.get('http://www.xicidaili.com/nt/{0}'.format(i), headers=header)
html = r.text
soup = BeautifulSoup(html)
table = soup.find('table', attrs={'id': 'ip_list'})
tr = table.find_all('tr')[1:]
# 解析得到代理ip的地址,端口,和类型
for item in tr:
tds = item.find_all('td')
print(tds[1].get_text())
temp_dict = {}
kind = tds[5].get_text().lower()
# exit()
if 'http' in kind:
temp_dict['http'] = "http://{0}:{1}".format(tds[1].get_text(), tds[2].get_text())
if 'https' in kind:
temp_dict['https'] = "https://{0}:{1}".format(tds[1].get_text(), tds[2].get_text())
proxy.append(temp_dict)
return proxy
def return_task():
return task_queue
def return_result():
return result_queue
class QueueManager(multiprocessing.managers.BaseManager):
pass
#启动主程序派发代理和url和代理
if __name__ == "__main__":
# 开启分布式支持
multiprocessing.freeze_support()
# 注册可以访问队列并得到结果的函数
QueueManager.register('get_task', callable=return_task)
QueueManager.register('get_result', callable=return_result)
#这里设置为192开头的局域ip地址即可局域多台机器使用也可以同一台电脑使用
#127开头只能在一台电脑上使用
manager = QueueManager(address=('127.0.0.1', 8888), authkey='password'.encode('utf-8'))
manager.start()
task = manager.get_task()
result = manager.get_result()
proxies = getProxyIp()
index_url = -1
while True:
for one_proxy in range(len(proxies)):
if task.qsize() < len(proxies):
print(task.qsize())
index_url+=1
if index_url>len(url_l)-1:
index_url=-1
task.put([url_l[index_url], proxies[one_proxy],
random.choice(random.choice([MY_USER_AGENT, iPhone_USER_AGENT, Android_USER_AGENT]))])
#从机程序
import requests
from multiprocessing import Pool
import multiprocessing.managers
from multiprocessing import Queue
import time
class QueueManager(multiprocessing.managers.BaseManager):
pass
def brash(url_data, proxy_dict, user_agent):
header = {'User-Agent': user_agent}
# header ={'Mozilla/5.0 (Linux; Android 4.4.2; 2014501 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/30.0.0.0 Mobile Safari/537.36 Html5Plus/1.0 (Immersed/25.0)'}
#提取网页内容程序放在这里
try:
r = requests.get(url_data, headers=header, proxies=proxy_dict, timeout=10)
except Exception as e:
pass # CONSTANT +=1
else:
# print(url_data, "su")
with open("log.txt","a") as f:
f.write(url_data+" successful \n")
time.sleep(1)
return None
def run(res):
brash(res[0], res[1], res[2])
if __name__ == '__main__':
# 开启分布式支持
multiprocessing.freeze_support()
# 注册可以访问队列并得到结果的函数
QueueManager.register('get_task')
QueueManager.register('get_result')
manager = QueueManager(address=('127.0.0.1', 8888), authkey='password'.encode('utf-8'))
manager.connect()
task = manager.get_task()
result = manager.get_result()
while True:
start=time.time()
pool = Pool(processes=32)
results = []
leth=task.qsize()
for _ in range(leth//5):
res = task.get()
results.append(pool.apply_async(run,(res,)))
for z in range(leth//5):
results[z].get()
pool.close()
pool.join()