initial commit of crawler skeleton
This commit is contained in:
28
crawler.py
Normal file
28
crawler.py
Normal file
@@ -0,0 +1,28 @@
|
||||
#!/usr/bin/env python
|
||||
'''
|
||||
Need a docstring.
|
||||
'''
|
||||
|
||||
import argparse
|
||||
from utils.helpers import (UrlPool, WebPage, sanitise_url, qualify_url)
|
||||
|
||||
def init_crawler(base_url=None):
|
||||
'''
|
||||
needs a docstring
|
||||
'''
|
||||
|
||||
|
||||
def run(args=None):
|
||||
'''
|
||||
needs a docstring.
|
||||
'''
|
||||
base_url = sanitise_url(args.url)
|
||||
print(base_url)
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
parser = argparse.ArgumentParser(description='Recursive web crawler')
|
||||
parser.add_argument("-u", "--url", required=True, help="Base url to crawl")
|
||||
args = parser.parse_args()
|
||||
|
||||
run(args)
|
||||
Reference in New Issue
Block a user