class Getter():
def __init__(self):
self.redis = RedisClient()
self.crawler = Crawler()
def is_over_threshold(self):
"""
判断是否达到了代理池限制
"""
if self.redis.count() >= POOL_UPPER_THRESHOLD:
print('已达到了代理池限制,暂停爬取')
return True
else:
return False
def run(self):
print('获取器开始执行')
if not self.is_over_threshold():
for callback_index in range(self.crawler.__CrawlFuncCount__):
callback = self.crawler.__CrawlFunc__[callback_index]
# 获取代理
proxies = self.crawler.get_proxies(callback)
sys.stdout.flush()
for proxy in proxies:
self.redis.add(proxy)
def crawl_xici_proxy(pagenumber):
url = "https://www.xicidaili.com/nn/{}"
client = RedisClient() #设置数据库为redis
for i in range(1, pagenumber + 1): #循环获取要访问的网址
new_url = url.format(i)
htmlcont = get_html(new_url, 'UTF-8')
selector = html.fromstring(htmlcont) #用selector获取网页源码
iplist = selector.xpath("//tr/td[2]/text()") #正则表达式获取其中的ip
portlist = selector.xpath("//tr/td[3]/text()")
for item in zip(iplist[1:-1], portlist[1:-1]): #合并ip和port
client.add(":".join(item))
class ValidityTester(object):
test_api = TEST_API
def __init__(self):
self._raw_proxies = None
self._usable_proxies = []
def set_raw_proxies(self, proxies):
self._raw_proxies = proxies
self._conn = RedisClient()
async def test_single_proxy(self, proxy):
"""
text one proxy, if valid, put them to usable_proxies.
"""
try:
async with aiohttp.ClientSession() as session:
try:
if isinstance(proxy, bytes):
proxy = proxy.decode('utf-8')
real_proxy = 'http://' + proxy
print('Testing', proxy)
async with session.get(
self.test_api,
proxy=real_proxy,
timeout=get_proxy_timeout) as response:
if response.status == 200:
self._conn.put(proxy)
print('Valid proxy', proxy)
except (ProxyConnectionError, TimeoutError, ValueError):
print('Invalid proxy', proxy)
except (ServerDisconnectedError, ClientResponseError,
ClientConnectorError) as s:
print(s)
pass
def test(self):
"""
aio test all proxies.
"""
print('ValidityTester is working')
try:
loop = asyncio.get_event_loop()
tasks = [
self.test_single_proxy(proxy) for proxy in self._raw_proxies
]
loop.run_until_complete(asyncio.wait(tasks))
except ValueError:
print('Async Error')
def valid_proxy(cycle=VALID_CHECK_CYCLE):
"""
Get half of proxies which in redis
"""
conn = RedisClient()
tester = ValidityTester()
while True:
print('Refreshing ip')
count = int(0.5 * conn.queue_len)
if count == 0:
print('Waiting for adding')
time.sleep(cycle)
continue
raw_proxies = conn.get(count)
tester.set_raw_proxies(raw_proxies)
tester.test()
time.sleep(cycle)
def check_pool(lower_threshold=POOL_LOWER_THRESHOLD,
upper_threshold=POOL_UPPER_THRESHOLD,
cycle=POOL_LEN_CHECK_CYCLE):
"""
If the number of proxies less than lower_threshold, add proxy
"""
conn = RedisClient()
adder = PoolAdder(upper_threshold)
while True:
if conn.queue_len < lower_threshold:
adder.add_to_queue()
time.sleep(cycle)
class Tester(object):
def __init__(self):
self.redis = RedisClient()
async def test_single_proxy(self, proxy):
"""
测试单个代理
:param proxy:
:return:
"""
conn = aiohttp.TCPConnector(verify_ssl=False)
async with aiohttp.ClientSession(connector=conn) as session:
try:
if isinstance(proxy, bytes):
proxy = proxy.decode('utf-8')
real_proxy = 'http://' + proxy
print('正在测试', proxy)
async with session.get(TEST_URL, proxy=real_proxy, timeout=5, allow_redirects=False) as response:
if response.status in VALID_STATUS_CODES:
self.redis.max(proxy)
print('代理可用', proxy)
else:
self.redis.decrease(proxy)
print('请求响应码不合法 ', response.status, 'IP', proxy)
except (ClientError, aiohttp.client_exceptions.ClientConnectorError, asyncio.TimeoutError, AttributeError):
self.redis.decrease(proxy)
print('代理请求失败', proxy)
def run(self):
"""
测试主函数
:return:
"""
print('测试器开始运行')
try:
count = self.redis.count()
print('当前剩余', count, '个代理')
for i in range(0, count, BATCH_TEST_SIZE):
start = i
stop = min(i + BATCH_TEST_SIZE, count)
print('正在测试第', start + 1, '-', stop, '个代理')
test_proxies = self.redis.batch(start, stop)
loop = asyncio.get_event_loop()
tasks = [self.test_single_proxy(proxy) for proxy in test_proxies]
loop.run_until_complete(asyncio.wait(tasks))
sys.stdout.flush()
time.sleep(5)
except Exception as e:
print('测试器发生错误', e.args)
def __init__(self):
self.redis = RedisClient()
from proxy_pool.db import RedisClient
conn = RedisClient()
def set(proxy):
result = conn.add(proxy)
print(proxy)
print('录入成功' if result else '录入失败')
def scan():
print('请输入代理, 输入exit退出读入')
while True:
proxy = input()
if proxy == 'exit':
break
set(proxy)
if __name__ == '__main__':
scan()
def __init__(self):
self.redis = RedisClient()
self.crawler = Crawler()
def __init__(self, threshold):
self._threshold = threshold
self._conn = RedisClient()
self._tester = ValidityTester()
self._crawler = FreeProxyGetter()
def set_raw_proxies(self, proxies):
self._raw_proxies = proxies
self._conn = RedisClient()
def get_conn(): #具柄：存在直接返回，不存在创建一个
if not hasattr(g, 'redis'):
g.redis = RedisClient()
return g.redis