fix: [moz500] Fix the confusion about Moz.com and Mozilla.com (#107)

fix: [moz500] Fix the confusion about Moz.com and Mozilla.com
pull/108/head
Steve Clement 2019-04-24 14:45:09 +09:00 committed by GitHub
commit 1cdd8d2e23
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 4 additions and 5 deletions

View File

@ -1,10 +1,10 @@
# The Moz Top 500 # The Moz Top 500
Moz's list of the top 500 domains and pages on the web. Mozs' (NOT to be confused with Mozilla) list of the top 500 domains and pages on the web.
Contains a list of the top 500 web pages ranked by the number of linking root domains. This data is sourced from the Mozcape web index of 818 Billion domains and 6 Trillion pages. Contains a list of the top 500 web pages ranked by the number of linking root domains. This data is sourced from the Mozcape web index of 818 Billion domains and 6 Trillion pages.
## Update list ## Update list
```bash ```bash
../../tools/generate_mozilla-top500.py |jq . > list.json ../../tools/generate_moz-top500.py |jq . > list.json
``` ```

View File

@ -1,7 +1,7 @@
{ {
"description": "Event contains one or more entries from the top 500 of the most used domains (Mozilla).", "description": "Event contains one or more entries from the top 500 of the most used domains (Mozilla).",
"version": 20190424, "version": 20190424,
"name": "Top 500 domains and pages from Mozilla", "name": "Top 500 domains and pages from https://moz.com/top500",
"type": "hostname", "type": "hostname",
"list": [ "list": [
"123-reg-expired.co.uk", "123-reg-expired.co.uk",

View File

@ -7,7 +7,6 @@ import json
import csv import csv
import os import os
# TODO: Include Top500 pages
# TODO: Include MozRank # TODO: Include MozRank
moz_url_domains = "https://moz.com/top500/domains/csv" moz_url_domains = "https://moz.com/top500/domains/csv"
@ -29,7 +28,7 @@ version = int(datetime.date.today().strftime('%Y%m%d'))
moz_warninglist['description'] = "Event contains one or more entries from the top 500 of the most used domains (Mozilla)." moz_warninglist['description'] = "Event contains one or more entries from the top 500 of the most used domains (Mozilla)."
d = datetime.datetime.now() d = datetime.datetime.now()
moz_warninglist['version'] = version moz_warninglist['version'] = version
moz_warninglist['name'] = "Top 500 domains and pages from Mozilla" moz_warninglist['name'] = "Top 500 domains and pages from https://moz.com/top500"
moz_warninglist['type'] = 'hostname' moz_warninglist['type'] = 'hostname'
moz_warninglist['list'] = [] moz_warninglist['list'] = []
moz_warninglist['matching_attributes'] = ['hostname', 'domain', 'uri', 'url'] moz_warninglist['matching_attributes'] = ['hostname', 'domain', 'uri', 'url']