def __init__(self, hostname=None, logger=None):
self.__hostname = hostname if hostname is not None else "http://127.0.0.0:5000"
self.__log = setup_console_logger(logger, "CallConnectHandler")
self.__jh = JsonHandler(hostname=self.__hostname, logger=self.__log)
self.__hh = HttpHandler(hostname=self.__hostname, logger=self.__log)
self.__log.debug("CallConnect handler initialized for: %s" %
self.__hostname)
class FlaskrilioHandler:
"""A simple wrapper for the local Flaskrilio service"""
def __init__(self, hostname=None, logger=None):
self.__hostname = hostname if hostname is not None else "http://127.0.0.0:5000"
self.__log = setup_console_logger(logger, "FlaskrilioHandler")
self.__jh = JsonHandler(hostname=self.__hostname, logger=self.__log)
self.__hh = HttpHandler(hostname=self.__hostname, logger=self.__log)
self.__log.debug("Flaskrilio handler initialized for: %s" % self.__hostname)
def get_home(self):
return self.__jh.get(endpoint="/")
def get_twiml(self, ctx):
self.__log.debug("Getting TwilML for an endpoint: %s" % ctx)
return self.__hh.get(endpoint=ctx)
def get_calls(self):
calls = self.__jh.get(endpoint="/calls")
self.__log.debug("Got calls: %s" % calls)
if calls is None:
return []
else:
return calls
def crawl_worker(self, url):
"""
This is the task that is being executed by the threadpool executor when it receive a url to do it's job
:param url: Url that is supposed to be getting links and assets from
:return: site_map_entry - dict(), links_with_issues_entry - set()
"""
if url is None:
raise ValueError("Url=%s has a None value" % url)
site_map_entry = dict()
links_with_issues_entry = set()
module_logger.info("Working on url=%s" % url)
try:
# Make a relative url into an absolute url
access_link = LinkHandler.reconstruct_link(self.start_url, url)
if access_link is None:
raise ValueError("Access link value: %s" % access_link)
elif not DomainRule.apply(self.start_url, access_link):
module_logger.info("url=%s is not in the same domain as %s" % (access_link, self.start_url))
module_logger.debug("Start url=%s site_map_entry=%s links_with_issues_entry=%s" % (self.start_url,
site_map_entry,
links_with_issues_entry))
return None, links_with_issues_entry
module_logger.debug("Going to open access_link=%s" % access_link)
except Exception as err:
module_logger.warn(err)
site_map_entry[url] = {'links': set(), 'assets': set()}
return None, links_with_issues_entry
try:
content = HttpHandler.fetch_url_content(access_link)
if content is None:
raise ValueError("Content of the url=%s is None" % url)
except ValueError as err:
module_logger.warn(err)
return None, links_with_issues_entry
except Exception as err:
module_logger.warn(err)
return None, links_with_issues_entry
links, assets = PageParser.parse_page_get_links(content)
site_map_entry[url] = {'links': links, 'assets': assets}
module_logger.info("Completed working on url=%s" % url)
module_logger.info("SiteMap=%s" % site_map_entry)
module_logger.info("Links with issues=%s" % links)
return site_map_entry, links_with_issues_entry
class CallConnectHandler:
"""A simple wrapper for Call Connect endpoints"""
def __init__(self, hostname=None, logger=None):
self.__hostname = hostname if hostname is not None else "http://127.0.0.0:5000"
self.__log = setup_console_logger(logger, "CallConnectHandler")
self.__jh = JsonHandler(hostname=self.__hostname, logger=self.__log)
self.__hh = HttpHandler(hostname=self.__hostname, logger=self.__log)
self.__log.debug("CallConnect handler initialized for: %s" % self.__hostname)
def get_new_caller_id(self):
caller_id = self.__jh.post(endpoint="/api/id", data="{}").json()['id']
self.__log.debug("Received new Caller ID: %s" % caller_id)
return caller_id
def get_redirect_to(self, caller_id, number):
payload = {
"id": caller_id,
"redirectTo": number
}
# use json.dumps to convert payload tupple into a string
redir = self.__jh.post(endpoint="/api/callers",
data=json.dumps(payload))
self.__log.debug("POST %s/api/callers payload: %s" % (self.__hostname, payload))
self.__log.debug("Received new redirect_to: %s" % redir.json())
return redir
def delete_caller_id(self, callerId):
self.__log.debug("Deleting callerId: %s" % callerId)
return self.__hh.delete(endpoint="/api/callers/%s" % callerId)
def get_callers_details(self, callerId):
self.__log.debug("Getting details for callerId: %s" % callerId)
return self.__jh.get(endpoint="/api/callers/%s" % callerId)
def get_number_pool(self):
pool = self.__jh.get(endpoint="/api/pool")
self.__log.debug("Got Number pool: %s" % pool.json())
return pool
class CallConnectHandler:
"""A simple wrapper for Call Connect endpoints"""
def __init__(self, hostname=None, logger=None):
self.__hostname = hostname if hostname is not None else "http://127.0.0.0:5000"
self.__log = setup_console_logger(logger, "CallConnectHandler")
self.__jh = JsonHandler(hostname=self.__hostname, logger=self.__log)
self.__hh = HttpHandler(hostname=self.__hostname, logger=self.__log)
self.__log.debug("CallConnect handler initialized for: %s" %
self.__hostname)
def get_new_caller_id(self):
caller_id = self.__jh.post(endpoint="/api/id", data="{}").json()['id']
self.__log.debug("Received new Caller ID: %s" % caller_id)
return caller_id
def get_redirect_to(self, caller_id, number):
payload = {"id": caller_id, "redirectTo": number}
# use json.dumps to convert payload tupple into a string
redir = self.__jh.post(endpoint="/api/callers",
data=json.dumps(payload))
self.__log.debug("POST %s/api/callers payload: %s" %
(self.__hostname, payload))
self.__log.debug("Received new redirect_to: %s" % redir.json())
return redir
def delete_caller_id(self, callerId):
self.__log.debug("Deleting callerId: %s" % callerId)
return self.__hh.delete(endpoint="/api/callers/%s" % callerId)
def get_callers_details(self, callerId):
self.__log.debug("Getting details for callerId: %s" % callerId)
return self.__jh.get(endpoint="/api/callers/%s" % callerId)
def get_number_pool(self):
pool = self.__jh.get(endpoint="/api/pool")
self.__log.debug("Got Number pool: %s" % pool.json())
return pool
class FlaskrilioHandler:
"""A simple wrapper for the local Flaskrilio service"""
def __init__(self, hostname=None, logger=None):
self.__hostname = hostname if hostname is not None else "http://127.0.0.0:5000"
self.__log = setup_console_logger(logger, "FlaskrilioHandler")
self.__jh = JsonHandler(hostname=self.__hostname, logger=self.__log)
self.__hh = HttpHandler(hostname=self.__hostname, logger=self.__log)
self.__log.debug("Flaskrilio handler initialized for: %s" %
self.__hostname)
def get_home(self):
return self.__jh.get(endpoint="/")
def get_twiml(self, ctx):
self.__log.debug("Getting TwilML for an endpoint: %s" % ctx)
return self.__hh.get(endpoint=ctx)
def get_calls(self):
calls = self.__jh.get(endpoint="/calls")
self.__log.debug("Got calls: %s" % calls)
if calls is None:
return []
else:
return calls
def __init__(self, hostname=None, logger=None):
self.__hostname = hostname if hostname is not None else "http://127.0.0.0:5000"
self.__log = setup_console_logger(logger, "FlaskrilioHandler")
self.__jh = JsonHandler(hostname=self.__hostname, logger=self.__log)
self.__hh = HttpHandler(hostname=self.__hostname, logger=self.__log)
self.__log.debug("Flaskrilio handler initialized for: %s" % self.__hostname)
def crawl(self, start_url=None):
"""
Single threaded webcrawler.
:param start_url: Starting url
:return: starting url (str), sitemap (dict), links with issues (set)
"""
if self.start_url is None and start_url is None:
raise ValueError("Start url cannot be None")
if start_url is not None:
self.start_url = start_url
site_map = dict()
visited = set()
links_with_issues = set()
queue = LifoQueue()
queue.put(self.start_url)
while not queue.empty():
next_link = queue.get()
module_logger.info("Retrieved url=%s from queue" % next_link)
try:
if FileExtensionRule.apply(next_link):
module_logger.info("Url=%s is a file asset" % next_link)
continue
except ValueError as err:
module_logger.warn(err)
try:
# Create an absolute url from a relative url
access_link = LinkHandler.reconstruct_link(self.start_url, next_link)
if access_link is None:
module_logger.warn("Currently working on next_link=%s - But access link value is None,"
"Something went wrong during the link construction" % next_link)
links_with_issues.add(next_link)
continue
elif access_link in visited:
module_logger.info("Already visited url=%s, skipping" % access_link)
continue
elif not DomainRule.apply(self.start_url, access_link):
module_logger.info("url=%s is not in the same domain as %s" % (access_link, self.start_url))
continue
else:
module_logger.info("Going to access url=%s constructed from %s" % (access_link, next_link))
except ValueError as err:
module_logger.warn(err)
links_with_issues.add(next_link)
continue
except Exception as err:
module_logger.error("An unexpected error during the link construction of url=%s" % next_link, err)
links_with_issues.add(next_link)
continue
try:
content = HttpHandler.fetch_url_content(access_link)
if content is None:
module_logger.warn("Unable to get content from link=%s" % access_link)
continue
except ValueError as err:
module_logger.warn("Link=%s has a value issue, value current is %s" % (access_link, content), err)
module_logger.exception(err)
continue
except Exception as err:
module_logger.warn("Something unexpected happened while fetching content of the url=%s"
% access_link)
module_logger.exception(err)
continue
# Get links and assets from HTML page
links, assets = PageParser.parse_page_get_links(content)
module_logger.debug("Add link=%s into already visited list" % next_link)
visited.add(next_link)
module_logger.info("Extracted from url=%s - links=%s assets=%s" % (access_link, links, assets))
for link in links:
if link not in visited:
queue.put(link)
module_logger.debug("Current link queue=%s" % str(queue))
site_map_record = {next_link: {'links': links, 'assets': assets}}
module_logger.info("Adding record into site map=%s" % site_map_record)
site_map.update(site_map_record)
module_logger.info("Crawling completed.")
module_logger.info("SiteMap=%s" % site_map)
module_logger.info("Links with issues=%s" % links_with_issues)
return self.start_url, site_map, links_with_issues
