def validate_robots(self):
"""
Confere o arquivo robots.txt dos sites e verifica condições de Dissalow
adicionando duas keys novas ao dict da cidade correspondente:
- has_robotstxt (True/False): responde a pergunta se tem ou não o arquivo robots.txt
- can_crawling (True/False): responde a pergunta se pode ou não fazer crawling
"""
try:
self.city['has_robotstxt'] = False
self.city['can_crawling'] = False
city_url = self.city['url']
city_url_robots = city_url + 'robots.txt'
robotstxt = requests.get(city_url_robots, timeout=30)
if robotstxt.status_code == 404:
self.city['can_crawling'] = False
if robotstxt.status_code == 200:
self.city['has_robotstxt'] = True
robotparser = urllib.robotparser.RobotFileParser()
robotparser.set_url(city_url_robots)
robotparser.read()
if robotparser.can_fetch('*', city_url):
self.city['can_crawling'] = True
self.validate_recommendations()
except requests.exceptions.RequestException as error:
print(dt.timestamp(dt.now()), self.city['city_name'], error)
def urlchecker(self, url):
if url is None:
return False
normalized_url = urltools.normalize(url)
robotparser = urllib.robotparser.RobotFileParser()
try:
url_comp = urlparse(normalized_url)
base_url = url_comp.scheme + "://" + url_comp.netloc + "/"
except:
self.logger.error("Cannot parse: " + url)
try:
robotparser.set_url(base_url + "robots.txt")
robotparser.read()
if not robotparser.can_fetch("*", normalized_url):
self.logger.error(url + " is excluded due to protocol")
return False
except:
self.logger.error("Cannot determine robots exclusion protocol: " +
url)
if normalized_url in self.visited_urls:
self.logger.debug(url + " Has been visited before! ")
return False
elif base_url in self.sites_times and self.sites_times[base_url] > int(
self.limit):
#
self.logger.debug(
url + " Times visiting this site have reach the limit ")
return False
elif 'cgi' in normalized_url:
return False
else:
return True
def validate_robots(self):
"""
Confere o arquivo robots.txt dos sites e verifica condições de Dissalow
adicionando duas keys novas ao dict da cidade correspondente:
- has_robotstxt (True/False): responde a pergunta se tem ou não o arquivo robots.txt
- can_crawling (True/False): responde a pergunta se pode ou não fazer crawling
"""
print(f'{self.city["city_name"]}: Verificação do arquivo robots.')
try:
self.city['timestamp'] = dt.timestamp(dt.now())
self.city['has_robotstxt'] = False
self.city['can_crawling'] = True
city_url = self.city['url']
city_url_robots = city_url + 'robots.txt'
robotstxt = requests.get(city_url_robots, timeout=30, headers={'user-agent': 'uscs/0.0.1'})
if robotstxt.status_code == 200:
self.city['has_robotstxt'] = True
robotparser = urllib.robotparser.RobotFileParser()
robotparser.set_url(city_url_robots)
robotparser.read()
if not robotparser.can_fetch('*', city_url):
self.city['can_crawling'] = False
print(f'{self.city["city_name"]}: Sem permissão para fazer crawling.')
if self.city['can_crawling']:
self.sourcecode = self.get_sourcecode()
self.validate_recommendations()
except requests.exceptions.RequestException as error:
print(dt.timestamp(dt.now()), self.city['_id'], self.city["city_name"], error)
def get_can_fetch(cls, node_url):
user_agent = cls.get_user_agent()
parsed_url = urlparse(node_url)
robot_url = f"{parsed_url.scheme}://{parsed_url.netloc}/robots.txt"
robotparser = urllib.robotparser.RobotFileParser()
robotparser.set_url(robot_url)
robotparser.read()
return robotparser.can_fetch(user_agent, node_url)
def checkRobotsForUrl(url):
# Extract base URL
parsedURL = urllib.parse.urlparse(url)
robotsURL = parsedURL.scheme + "://" + parsedURL.netloc + "/robots.txt"
try:
robotparser = urllib.robotparser.RobotFileParser()
robotparser.set_url(robotsURL)
robotparser.read()
can_fetch = robotparser.can_fetch("*", url)
return can_fetch
except:
return True
def get_data(url, robotparser):
# doesn't work...Because just match /dontgohere/, now it works
if robotparser.can_fetch("*", suburl(url)):
request = urllib.request.Request(url=url, headers=headers)
print("Now URL:" + url)
response = urllib.request.urlopen(request)
data = response.read()
data = data.decode('utf-8')
history.append(url)
# print("All History:"+''.join(str(e) for e in history))
return data
else:
return None
def link_crawler(seed_url, link_regex):
crawl_queue = [seed_url]
seen = set(crawl_queue)
while crawl_queue:
url = crawl_queue.pop()
rp = robotparser.can_fetch()
html = download(url)
for link in get_links(html):
if re.match(link_regex, link):
link = urljoin(seed_url, link)
if link not in seen:
seen.add(link)
crawl_queue.append(link)
import urllib.robotparser
from urllib.parse import urlparse
user_agent = 'unpackbot'
url = "https://buzzfeed.com/contests"
parsed_url = urlparse(url)
robot_url = f"{parsed_url.scheme}://{parsed_url.netloc}/robots.txt"
print(url, robot_url)
robotparser = urllib.robotparser.RobotFileParser()
robotparser.set_url(robot_url)
robotparser.read()
can_fetch = robotparser.can_fetch(user_agent, url)
print(can_fetch)
def check_robot(url, user_agent):
robotparser = urllib.robotparser.RobotFileParser()
robotparser.set_url(url+'/robots.txt')
robotparser.read()
print(robotparser.can_fetch(user_agent,url))
return robotparser.can_fetch(user_agent, url)
def check_robot(url, **kwargs):
user_agent = 'python-requests/2.18.4 (Compatible; John Doe)'
robotparser = urllib.robotparser.RobotFileParser()
robotparser.set_url(url)
robotparser.read()
return robotparser.can_fetch(user_agent, url)
