rra/dafr
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

about_crawler now properly uses functions from fedicrawler

Browse Source
This commit is contained in:
rra 2020-05-05 16:55:59 +02:00
parent f62bff244c
commit 2278cd9d3d
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
about_collector.py
View File

@ -1,11 +1,11 @@
#!/bin/env python3
#!/usr/bin/env python3
# a tool for collecting mastodon /about/ & ToS and CoC pages.
# (c) roel roscam abbing 2020
# gplv3
import os, time, json
import fedicrawler
from fedicrawler import only_netloc, multi_filter
filters = [fedicrawler.only_netloc]
filters = [only_netloc]
scrape_data = json.loads(open('instance_scrape.json').read())
@ -26,7 +26,7 @@ def find_mastodon_instances(scrape_data):
if scrape_data[i]['nodeinfo']['software']['name'].lower() == 'mastodon':
mastodon_instances.append(i)
#mastodon_instances = fedicrawler.multi_filter(filters,mastodon_instances)
mastodon_instances = list(multi_filter(filters,mastodon_instances))
return mastodon_instances
@ -37,7 +37,6 @@ options = Options()
options.add_argument('-headless')
browser = webdriver.Firefox(options=options)
#browser.set_window_size(1024, 768) # set the window size that you need
for mi in find_mastodon_instances(scrape_data):