Add argument to skip scraping and just spit out a graph

This commit is contained in:
Thomas Wade 2018-09-30 15:02:45 +09:30
parent 65a5a5c63b
commit 3588e5937f

View File

@ -43,6 +43,16 @@ from selenium.webdriver.support import expected_conditions
from selenium.webdriver.chrome.options import Options from selenium.webdriver.chrome.options import Options
from bs4 import BeautifulSoup from bs4 import BeautifulSoup
from collections import Counter from collections import Counter
from argparse import ArgumentParser
##### Parse arguments #######################################
parser = ArgumentParser()
parser.add_argument('-d', '--dump', help='skip scraping and process whatever is shelved', action='store_true')
args = parser.parse_args()
if args.dump:
print('Dump option specified, will skip scraping')
##### Set up NetworkX ####################################### ##### Set up NetworkX #######################################
@ -52,6 +62,7 @@ print('NetworkX initialised')
##### Set up WebDriver with Chrome ########################## ##### Set up WebDriver with Chrome ##########################
if not args.dump:
chrome_options = Options() chrome_options = Options()
# Start headless so we can run on a server overnight # Start headless so we can run on a server overnight
@ -343,7 +354,7 @@ with shelve.open('shelf.db') as shelf:
if 'iterator' in shelf.keys(): if 'iterator' in shelf.keys():
iterator = shelf['iterator'] iterator = shelf['iterator']
if not args.dump:
while iterator <= MAX_DEGREE: while iterator <= MAX_DEGREE:
for user_str in users_to_process: for user_str in users_to_process:
print('Processing ' + user_str + ' (distance ' + str(iterator) + ')') print('Processing ' + user_str + ' (distance ' + str(iterator) + ')')