simplify UrlPoolManager to use a set instead of a dict
This commit is contained in:
@@ -9,28 +9,22 @@ class UrlPoolManager(object):
|
||||
'''
|
||||
|
||||
def __init__(self):
|
||||
self.url_pool = dict()
|
||||
self.not_crawled = 0
|
||||
self.crawled = 1
|
||||
self.invalid = 2
|
||||
self.url_pool = set()
|
||||
|
||||
def check_duplicate(self, new_url):
|
||||
for url, status in self.url_pool.items():
|
||||
if url == new_url:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
'''
|
||||
Checks if a URL exists in the current pool.
|
||||
'''
|
||||
if new_url in self.url_pool:
|
||||
return True
|
||||
else:
|
||||
return False
|
||||
|
||||
def invalidate_url(self, url):
|
||||
self.url_pool[url] = self.invalid
|
||||
self.url_pool.remove(url)
|
||||
|
||||
def add_to_list(self, url):
|
||||
self.url_pool[url] = self.not_crawled
|
||||
# calculate depth
|
||||
# add link, crawled status to url_pool
|
||||
|
||||
def mark_as_crawled(self, url):
|
||||
self.url_pool[url] = self.crawled
|
||||
self.url_pool.add(url)
|
||||
|
||||
|
||||
def clean_base_url(url):
|
||||
|
||||
Reference in New Issue
Block a user