def dealUrl2Request(self, url, origin):
origin = Url(origin)
url = Url(url)
if not url.startswith('http://') and not url.startswith('https://'):
if url.startswith('//'):
url = 'http:' + url
elif url.startswith('/'):
url = origin.getHost()[2] + url
else:
origin = origin.getUrlDir()
url = origin + url
url = url.simplifyUrl()
return url
def dealUrl2Request(self, url, origin):
origin = Url(origin)
url = Url(url)
if not url.startswith('http://') and not url.startswith('https://'):
if url.startswith('//'):
url = 'http:' + url
elif url.startswith('/'):
url = origin.getHost()[2] + url
else:
origin = origin.getUrlDir()
url = origin + url
url = url.simplifyUrl()
return url
class Crawler:
def __init__(self, url):
self.main_url = Url(self.requestGet(url).url)
self.host_option, self.host, self.host_url = self.main_url.getHost()
self.queue_resource = None
self.queue_document = None
self.set = None
self.document_task = None
self.source_task = None
def __del__(self):
# del self.document_task
# del self.queue_document
# del self.source_task
# del self.queue_resource
print 'del c'
def start(self, is_continue=False):
if is_continue:
self.queue_resource = Queue.load(logs_path + 'queue_resource.json')
self.queue_document = Queue.load(logs_path + 'queue_document.json')
self.set = UrlSet.load(logs_path + 'url_set.json')
else:
self.queue_resource = Queue(logs_path + 'queue_resource.json')
self.queue_document = Queue(logs_path + 'queue_document.json')
self.set = UrlSet(logs_path + 'url_set.json')
self.document_task = Task(self.queue_document, doc_pool_max)
self.document_task.initTaskWork(self.getDocument)
self.source_task = Task(self.queue_resource, res_pool_max)
self.source_task.initTaskWork(self.requestSource)
self.main_url = urlTools.dealUrl2Request(self.main_url, self.main_url)
print self.main_url, self.host
file_path, file_name, html_url = urlTools.dealUrl2File(
self.main_url, self.main_url, self.host, True)
self.queue_document.push([self.main_url, file_path, file_name, 0, 0])
print "file_path:" + file_path, "file_name:" + file_name, "html_url:" + html_url
self.document_task.start()
def requestGet(self, url):
wait = random.random() * (wait_time[1] - wait_time[0])
sleep(wait)
timeout = Timeout(request_timeout)
timeout.start()
try:
req = requests.get(url=url,
verify=True,
headers=headers,
proxies=proxies)
except IncompleteRead:
pass
# todo:未知错误，暂还未查清
timeout.cancel()
return req
def saveFile(self, file_path, file_name, bytes):
path = Url(output + file_path)
path = path.addUrlEnd()
if not os.path.exists(path):
os.makedirs(path)
try:
f = open(path + file_name, "wb")
f.write(bytes)
f.close()
except IOError, e:
print 'save Error: ', e, 'path: ', path, 'name: ', file_name
class Crawler:
def __init__(self, url):
self.main_url = Url(self.requestGet(url).url)
self.host_option, self.host, self.host_url = self.main_url.getHost()
self.queue_resource = None
self.queue_document = None
self.set = None
self.document_task = None
self.source_task = None
def __del__(self):
# del self.document_task
# del self.queue_document
# del self.source_task
# del self.queue_resource
print 'del c'
def start(self, is_continue=False):
if is_continue:
self.queue_resource = Queue.load(logs_path + 'queue_resource.json')
self.queue_document = Queue.load(logs_path + 'queue_document.json')
self.set = UrlSet.load(logs_path + 'url_set.json')
else:
self.queue_resource = Queue(logs_path + 'queue_resource.json')
self.queue_document = Queue(logs_path + 'queue_document.json')
self.set = UrlSet(logs_path + 'url_set.json')
self.document_task = Task(self.queue_document, doc_pool_max)
self.document_task.initTaskWork(self.getDocument)
self.source_task = Task(self.queue_resource, res_pool_max)
self.source_task.initTaskWork(self.requestSource)
self.main_url = urlTools.dealUrl2Request(self.main_url, self.main_url)
print self.main_url, self.host
file_path, file_name, html_url = urlTools.dealUrl2File(self.main_url, self.main_url, self.host, True)
self.queue_document.push([self.main_url, file_path, file_name, 0, 0])
print "file_path:" + file_path, "file_name:" + file_name, "html_url:" + html_url
self.document_task.start()
def requestGet(self, url):
wait = random.random() * (wait_time[1] - wait_time[0])
sleep(wait)
timeout = Timeout(request_timeout)
timeout.start()
try:
req = requests.get(url=url, verify=True, headers=headers, proxies=proxies)
except IncompleteRead:
pass
# todo:未知错误，暂还未查清
timeout.cancel()
return req
def saveFile(self, file_path, file_name, bytes):
path = Url(output + file_path)
path = path.addUrlEnd()
if not os.path.exists(path):
os.makedirs(path)
try:
f = open(path + file_name, "wb")
f.write(bytes)
f.close()
except IOError, e:
print 'save Error: ', e, 'path: ', path, 'name: ', file_name