def __init__(self, crawler):
print(
'[' +
time.strftime('%Y/%m/%d %H:%M:%S', time.localtime(time.time())) +
']', "【init】")
self.proxy = None # 默认代理为空，使用真实IP
self.db = RedisClient()
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
:return:
"""
if self.redis.count() >= POOL_UPPER_THRESHOLD:
return True
else:
return False
def run(self):
print('获取器开始执行')
if not self.is_over_threshold():
for callback_label in range(self.crawler.__CrawlFuncCount__):
callback = self.crawler.__CrawlFunc__[callback_label]
proxies = self.crawler.get_proxies(callback)
sys.stdout.flush()
for proxy in proxies:
print(proxy, type(proxy))
self.redis.add(proxy)
def control_add_proxy():
proxy_min = PROXY_MIN
conn = RedisClient()
addr = PoolAdder()
cycle = CYCLE_TIME
while True:
if conn.count() < PROXY_MAX:
addr.add_to_redis()
time.sleep(cycle)
def valid_proxies(cycle=VALID_CHECK_CYCLE):
conn = RedisClient()
tester = ValidityTester()
while True:
print("check valid proxies")
count = int(conn.zset_len / 2)
if count == 0:
print("add new valid proxies")
time.sleep(cycle)
continue
proxies = conn.get(count)
tester.set_raw_proxies(proxies)
tester.test()
time.sleep(cycle)
def control_test_proxy():
conn = RedisClient()
cycle = CYCLE_TIME
tester = ValidityTester()
while True:
print('Refreshing ip')
count = int(0.5 * conn.count())
if count == 0:
print('Waiting for adding')
time.sleep(cycle)
continue
raw_proxies = conn.get(count)
tester.set_test_procies(raw_proxies)
tester.test()
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=15,
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 run(self):
print('Ip processing running')
RedisClient().flush()
valid_process = Process(target=Schedule.valid_proxies)
check_process = Process(target=Schedule.check_pool)
valid_process.start()
check_process.start()
class PoolAdder(object):
def __init__(self):
self.proxy_max = PROXY_MAX
self.tester = ValidityTester()
self.getter = FreeProxyGetter()
self.conn = RedisClient()
def is_picture(self):
if self.conn.count() < self.proxy_max:
return True
return False
def add_to_redis(self):
proxy_count = 0
while self.is_picture():
for callback_label in range(self.getter.__CrawlFuncCount__):
callback = self.getter.__CrawlFunc__[callback_label]
raw_proxies = self.getter.get_raw_proxies(callback)
self.tester.set_test_procies(raw_proxies)
self.tester.test()
proxy_count += len(raw_proxies)
if not self.is_picture():
print('代理ip队列已满')
break
if proxy_count == 0:
print('请求不到ip')
break
def check_pool(cycle=POOL_LEN_CHECK_CYCLE,
min=POOL_LOWER_THRESHOLD,
max=POOL_UPPER_THRESHOLD):
conn = RedisClient()
adder = ProxyPoolAdder(max)
while True:
if conn.zset_len <= min:
adder.add_to_zset()
time.sleep(cycle)
class Getter():
def __init__(self):
self.redis = RedisClient()
self.crawler = Crawler()
def is_over_threshold(self):
if self.redis.count() >= POOL_UPPER_THRESHOLD:
return True
return False
def run(self):
print('获取器开始执行')
if not self.is_over_threshold():
for callback_label in range(self.crawler.__CrawlFuncCount__):
callback = self.crawler.__crawlFunc__[callback_label]
proxies = self.crawler.get_proxies(callback)
for proxy in proxies:
self.redis.add(proxy)
class ValidityTester():
test_api = TEST_API
header = {
'User-Agent':
'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.26 Safari/537.36 Core/1.63.5702.400 QQBrowser/10.2.1893.400'
}
def __init__(self):
self.test_proxies = []
def set_test_procies(self, proxies):
self.test_proxies = proxies
self.conn = RedisClient()
def test_single_proxy(self, proxy):
try:
if isinstance(proxy, bytes):
proxy = proxy.decode('utf-8')
real_proxy = 'http://' + proxy
r = requests.get(url=self.test_api,
proxies={'http://': real_proxy},
headers=self.header)
if r.status_code == 200:
self.conn.put(proxy)
print('验证成功：', proxy)
else:
print('验证失败：', proxy)
except:
print('请求失败：', proxy)
def test(self):
try:
test_proxy_pool = threadpool.ThreadPool(5)
test_proxy_requests = threadpool.makeRequests(
self.test_single_proxy, self.test_proxies)
for tpr in test_proxy_requests:
test_proxy_pool.putRequest(tpr)
test_proxy_pool.wait()
self.test_proxies = []
except:
self.test()
class QichachaProxyMiddleware(object):
def __init__(self):
self.proxyData = RedisClient()
self.logger = logging.getLogger(__name__)
def process_request(self, request, spider):
if request.meta.get('retry_times'):
proxy = self.proxyData.random_proxy()
if proxy:
uri = 'https://{}'.format(proxy)
self.logger.debug('使用代理' + proxy)
request.meta['proxy'] = uri
request.meta['downlaod_timeout'] = 20
class ValidityTester(object):
test_api = TEST_API
def __init__(self):
self._raw_proxies = None
self._available_proxies = []
self._conn = RedisClient()
self.logger = logging.getLogger(__name__)
def set_raw_proxies(self, proxies):
self._raw_proxies = proxies
async def test_one_proxy(self, proxy):
async with aiohttp.ClientSession() as session:
if isinstance(proxy, bytes):
proxy = proxy.decode('utf-8')
real_proxy = "http://" + proxy
try:
async with session.get(ValidityTester.test_api,
proxy=real_proxy,
timeout=10) as rep:
if rep.status == 200:
self._conn.add(proxy)
self.logger.info("valid proxy:" + proxy)
except Exception as e:
self.logger.error("invalid proxy:" + proxy)
def test(self):
"""
aio test all proxies.
"""
print('ValidityTester is working')
try:
loop = asyncio.get_event_loop()
tasks = [self.test_one_proxy(proxy) for proxy in self._raw_proxies]
loop.run_until_complete(asyncio.wait(tasks))
except ValueError:
self.logger.error('Async Error')
class Tester(object):
def __init__(self):
self.redis = RedisClient()
async def test_single_proxy(self, proxy):
"""
测试单个代理
:param proxy: 单个代理
:return: None
"""
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=10) as response:
if response.status in VALID_STATUS_CODES:
self.redis.max(proxy)
else:
self.redis.decrease(proxy)
print("请求响应码不和法", proxy)
except (
ClientError,
ProxyConnectionError,
ServerConnectionError,
TimeoutError,
AttributeError,
):
self.redis.decrease(proxy)
print("代理请求失败", proxy)
except Exception as e:
print(e)
def run(self):
"""
测试主函数
:return:
"""
print("测试器开始运行")
try:
proxies = self.redis.all()
loop = asyncio.get_event_loop()
# 批量测试
for i in range(0, len(proxies), BATCH_TEST_SIZE):
test_proxies = proxies[i:i + BATCH_TEST_SIZE]
tasks = [self.test_single_proxy(proxy) for proxy in proxies]
loop.run_until_complete(asyncio.wait(tasks))
time.sleep(5)
except Exception as e:
print("测试器发生错误", e.args)
class Getter():
def __init__(self):
self.redis = RedisClient()
self.crawler = Crawler()
def is_over_threshold(self):
"""
Compare to the capacity of proxy pool.
"""
if self.redis.count() >= POOL_UPPER_THRESHOLD:
return True
else:
return False
def run(self):
logger.debug('Getter is running.')
if not self.is_over_threshold():
for callback_label in range(self.crawler.__CrawlFuncCount__):
callback = self.crawler.__CrawlFunc__[callback_label]
# 获取代理
proxies = self.crawler.get_proxies(callback)
sys.stdout.flush()
for proxy in proxies:
self.redis.add(proxy)
class Tester(object):
def __init__(self):
self.redis = RedisClient()
async def test_single_proxy(self, proxy):
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=15) 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', proxy)
except (ClientError, ClientConnectionError, TimeoutError,
AttributeError):
self.redis.decrease(proxy)
print('代理请求失败', proxy)
def run(self):
print('测试器开始运行')
try:
proxies = self.redis.all()
loop = asyncio.get_event_loop()
for i in range(0, len(proxies), BATCH_TEST_SIZE):
test_proxies = proxies[i:i + BATCH_TEST_SIZE]
tasks = [
self.test_single_proxy(proxy) for proxy in test_proxies
]
loop.run_until_complete(asyncio.wait(tasks))
time.sleep(5)
except Exception as e:
print('测试器发生错误', e.args)
def __init__(self):
self.redis = RedisClient()
def __init__(self):
self.redis = RedisClient()
self.crawler = Crawler()
def set_test_procies(self, proxies):
self.test_proxies = proxies
self.conn = RedisClient()
def __init__(self):
self.proxy_max = PROXY_MAX
self.tester = ValidityTester()
self.getter = FreeProxyGetter()
self.conn = RedisClient()
class SuperspiderDownloaderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the downloader middleware does not modify the
# passed objects.
def __init__(self, crawler):
print(
'[' +
time.strftime('%Y/%m/%d %H:%M:%S', time.localtime(time.time())) +
']', "【init】")
self.proxy = None # 默认代理为空，使用真实IP
self.db = RedisClient()
def infoprint(self, message):
print('[' +
time.strftime('%Y/%m/%d %H:%M:%S', time.localtime(time.time())) +
']【Info】' + message)
def get_proxy(self):
"""随机获取代理"""
try:
proxy = self.db.get_random().decode('utf-8')
return "http://{}".format(proxy)
except Exception as e:
print(
'[' + time.strftime('%Y/%m/%d %H:%M:%S',
time.localtime(time.time())) + ']',
'【获取代理失败!】')
return None
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls(crawler)
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s
def process_request(self, request, spider):
# Called for each request that goes through the downloader
# middleware.
# Must either:
# - return None: continue processing this request
# - or return a Response object
# - or return a Request object
# - or raise IgnoreRequest: process_exception() methods of
# installed downloader middleware will be called
"""处理请求"""
self.infoprint('【是否重试】:' + ('是' if request.meta.get('retry') else '否'))
old_proxy = request.meta.get('proxy')
if self.proxy is None or old_proxy is None or self.proxy == request.meta.get(
'proxy'):
# 请求被重来，更换代理
proxy = self.get_proxy()
self.infoprint('更换代理为:{}'.format(proxy))
if proxy:
self.proxy = proxy
request.meta['proxy'] = self.proxy
spider.info('【request】' + self.proxy + ' URL:' + request.url)
def process_response(self, request, response, spider):
# Called with the response returned from the downloader.
# Must either;
# - return a Response object
# - return a Request object
# - or raise IgnoreRequest
"""处理响应"""
if response.status != 200:
if response.status == 302:
self.infoprint('【被拦截】:' + self.proxy)
spider.logger.warning('【被拦截】:' + self.proxy)
elif response.status == 404:
self.infoprint('【无法找到文件】:' + self.proxy + ' URL:' +
request.url)
spider.logger.warning('【无法找到文件】:' + self.proxy + ' URL:' +
request.url)
else:
self.infoprint('【未知】' + self.proxy + ' ' +
str(response.status) + ' URL:' + request.url)
spider.logger.warning('【未知】' + self.proxy + ' ' +
str(response.status) + ' URL:' +
request.url)
return self.get_retry_request(request)
elif '用户访问安全认证' in response.text:
self.infoprint('【出现安全认证】' + response.url)
spider.logger.warning('【出现安全认证】' + response.url)
return self.get_retry_request(request)
return response
def process_exception(self, request, exception, spider):
# Called when a download handler or a process_request()
# (from other downloader middleware) raises an exception.
# Must either:
# - return None: continue processing this exception
# - return a Response object: stops process_exception() chain
# - return a Request object: stops process_exception() chain
try:
oserror = str(exception.osError)
if oserror == "10060" or oserror == "10061":
self.infoprint('【exception】' + request.url + ' ' +
str(exception.args))
spider.logger.error('【exception】' + request.url + ' ' +
str(exception.args))
else:
self.infoprint('【exception】' + request.url + ' ' +
str(exception.osError))
spider.logger.error('【exception】' + request.url + ' ' +
str(exception.osError))
except:
try:
self.infoprint('【exception】' + request.url + ' ' +
str(exception))
spider.logger.error('【exception】' + request.url + ' ' +
str(exception))
except:
pass
pass
self.infoprint('【请求错误】重试')
spider.logger.info('【请求错误】重试')
# 重试
return self.get_retry_request(request)
def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name)
def get_retry_request(self, request):
"""获取要重试的请求"""
try:
self.proxy = None # 重置代理
retry_request = request.copy()
retry_request.dont_filter = True # 禁止去重
retry_request.meta['retry'] = time.time()
return retry_request
except Exception as e:
self.infoprint('【get_retry_request】【获取要重试的请求出错】' + str(e))
return None
def get_conn():
if not hasattr(g, 'redis'):
g.redis = RedisClient()
return g.redis
from ProxyPool.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, threshold):
self._conn = RedisClient()
self._crawl = FreeProxyGetter()
self._tester = ValidityTester()
self._threshold = threshold
self.logger = logging.getLogger(__name__)
class Tester:
def __init__(self):
self.redis = RedisClient()
async def test_single_proxy(self, proxy):
"""
Test the availability of a proxy.
And maximize its score if available else decrease its score.
: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 # url应包括协议，浏览器访问不加协议会默认用http
logger.debug('Testing {}'.format(proxy))
async with session.get(TEST_URL,
proxy=real_proxy,
timeout=15,
allow_redirects=False) as response:
if response.status in VALID_STATUS_CODES:
logger.debug('Proxy {} is OK'.format(proxy))
self.redis.maximize(proxy)
else:
logger.warning(
'Failed to use proxy {} because the response code was {}'
.format(proxy, response.status))
self.redis.decrease(proxy)
except (ClientError,
aiohttp.client_exceptions.ClientConnectorError,
asyncio.TimeoutError, AttributeError) as e:
self.redis.decrease(proxy)
logger.warning('Failed to use proxy {} because of {}'.format(
proxy, repr(e)))
def run(self):
"""
Run tester.
:return:
"""
logger.debug('Tester is running.')
try:
count = self.redis.count()
logger.info(
'There are {} proxy (proxies) in proxy pool now.'.format(
count))
for i in range(0, count, BATCH_TEST_SIZE):
start = i
stop = min(i + BATCH_TEST_SIZE, count)
# 分批测试防止内存开销过大
logger.debug(
'Testing proxies with index between {} and {}.'.format(
start + 1, stop))
test_proxies = self.redis.batch(start, stop)
# 异步测试加快速度
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)
logger.info('Testing finished')
except Exception as e:
logger.warning('Tester error {}'.format(e.args))
def __init__(self):
self.proxyData = RedisClient()
self.logger = logging.getLogger(__name__)
def __init__(self):
self._raw_proxies = None
self._available_proxies = []
self._conn = RedisClient()
self.logger = logging.getLogger(__name__)
def get_proxy():
cli = RedisClient()
return cli.random()
