Last active
September 12, 2018 18:11
-
-
Save dayllanmaza/6d9c55a80da837fc68a3a6af310c01a8 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import csv | |
import pprint | |
import re | |
import sys | |
import time | |
import calendar | |
import datetime | |
import requests | |
REGEX_CASE_RESOLVED = r'{{\s?(resolved|atop|archive\stop)' | |
REGEX_USER_TALK_DATES = r'\[{2}User[\s_]talk\:(?:[^(?:\]\]|\||#)])*[^\]\]]*\]\]\)?\s(\d{2}:\d{2},\s\d{2}\s\w+\s\d{4})' | |
REGEX_LINKS = r'((?:https|http):\/{2}(?:www\.)?[^]|\s]+)' | |
REGEX_SPECIAL_TEMPLATE = r'\[{2}(Special:[^\||\]]+)' | |
REGEX_WP_LINK = r'\[{2}((?:WP|Wikipedia):\s?[^\|\]\]]*)' | |
# noticeboard_page = 'Wikipedia:Administrators\'_noticeboard/Archive' | |
noticeboard_page = 'Wikipedia:Administrators\'_noticeboard/IncidentArchive' | |
base_url = 'https://en.wikipedia.org/w/api.php?format=json&action=parse&page=' | |
def main(): | |
path = os.path.dirname(os.path.abspath(__file__)) + '/' | |
with open(path + 'ani_links.csv', 'w') as csvfile: | |
#with open(path + 'an_links.csv', 'w') as csvfile: | |
writer = csv.writer(csvfile, dialect='excel') | |
headers = ['title', 'url', 'resolved', 'open date', 'diff total', 'diff links', | |
'special total', 'special links', 'other wiki total', 'other wiki', 'timeline total', | |
'timeline links', 'toollabs total', 'toollabs links', 'others total', 'others links'] | |
writer.writerow(headers) | |
for i in range(981, 992): | |
# for i in range(293, 303): | |
cases = fetch_archive_cases(i) | |
if cases: | |
writer.writerows(cases) | |
def fetch_archive_cases(index): | |
page_url = base_url + noticeboard_page + str(index) + '&prop=sections' | |
data = requests.get(page_url).json() | |
print(page_url) | |
sections = data['parse']['sections'] | |
cases = [] | |
for section in sections: | |
if section['toclevel'] != 1: # we only care about top level sections | |
continue | |
if not section['index']: | |
print('Could not parse: ' + section['anchor']) | |
continue | |
section_url = base_url + noticeboard_page + str(index) + '&prop=wikitext|externallinks|iwlinks' + '§ion=' + section['index'] | |
data = fetch_case_data(section_url) | |
wikitext = str(data['wikitext']) | |
case_url = 'https://en.wikipedia.org/wiki/' + section['fromtitle'] + '#' + section['anchor'] | |
print(case_url) | |
links = get_links(wikitext) | |
case = [ | |
section['line'], # title | |
case_url, # url | |
is_case_resolved(wikitext), # resolved | |
get_case_open_date(wikitext), # open date | |
len(links['diff']), # diff total | |
'\n'.join(links['diff']), # diff links | |
len(links['special']), # special pages count | |
'\n'.join(links['special']), # special pages links | |
len(links['other_wiki']), # other wiki links count | |
'\n'.join(links['other_wiki']), # other wiki links | |
len(links['timeline']), # timeline count | |
'\n'.join(links['timeline']), # timeline links | |
len(links['toollabs']), # toollabs count | |
'\n'.join(links['toollabs']), # toollabs links | |
len(links['other']), # other links count | |
'\n'.join(links['other']) # other links | |
] | |
cases.append(case) | |
return cases | |
def fetch_case_data(url): | |
print(url) | |
data = requests.get(url).json() | |
return data['parse'] | |
def is_case_resolved(case): | |
return re.search(REGEX_CASE_RESOLVED, case, re.IGNORECASE) is not None | |
def get_case_open_date(case): | |
matches = re.findall(REGEX_USER_TALK_DATES, case, re.IGNORECASE) | |
if not matches: | |
return 'Not found' | |
dates = [] | |
for date in matches: | |
ts = calendar.timegm(time.strptime(date, '%H:%M, %d %B %Y')) | |
dates.append(ts) | |
dates.sort() | |
return datetime.datetime.fromtimestamp(dates[0]).isoformat() | |
def get_links(case): | |
links = { | |
'diff': [], | |
'special': [], | |
'other_wiki': [], | |
'timeline': [], | |
'toollabs': [], | |
'other': [] | |
} | |
# get urls from the case wikitext | |
matches = re.findall(REGEX_LINKS, case) | |
if matches: | |
for link in matches: | |
if re.search(r'(?:diff=|Special:Diff)', link, re.IGNORECASE): | |
links['diff'].append(link) | |
elif re.search(r'Special:[^Diff]', link, re.IGNORECASE): | |
links['special'].append(link) | |
elif re.search(r'wikipedia\.org.+[^(?:Special|diff)]', link, re.IGNORECASE): | |
links['other_wiki'].append(link) | |
elif link.find('/interaction-timeline') != -1: | |
links['timeline'].append(link) | |
elif link.find('tools.wmflabs.org') != -1: | |
links['toollabs'].append(link) | |
else: | |
links['other'].append(link) | |
# get template links | |
matches = re.findall(REGEX_SPECIAL_TEMPLATE, case, re.IGNORECASE) | |
if matches: | |
for special_page in matches: | |
link = 'https://en.wikipedia.org/wiki/' + special_page | |
if special_page.find('Diff') != -1: | |
links['diff'].append(link) | |
else: | |
links['special'].append(link) | |
matches = re.findall(REGEX_WP_LINK, case, re.IGNORECASE) | |
if matches: | |
for wiki_page in matches: | |
link = 'https://en.wikipedia.org/wiki/' + wiki_page | |
links['other_wiki'].append(link) | |
return links | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment