1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
#!/usr/bin/python3
# encoding=utf-8
#
# Copyright © 2015 Alexandre Detiste <alexandre@detiste.be>
# SPDX-License-Identifier: GPL-2.0-or-later
# a simple spider to locate Wikipedia url
# in per-engine-wiki pages
# we don't rescan games we already have
import sys
import time
import urllib.request
from bs4 import BeautifulSoup
from game_data_packager.game import load_games
from game_data_packager.util import AGENT
CSV = 'data/wikipedia.csv'
try:
todo = sys.argv[1]
except IndexError:
todo = '*'
urls = dict()
with open(CSV, 'r', encoding='utf8') as f:
for line in f.readlines():
line = line.strip()
if not line:
continue
shortname, url = line.split(';', 1)
urls[shortname] = url
def is_wikipedia(href):
return href and "wikipedia" in href
for shortname, game in load_games(game=todo).items():
if not game.wiki:
continue
if shortname in urls:
continue
print('processing %s ...' % shortname)
url = game.wikibase + game.wiki
html = urllib.request.urlopen(urllib.request.Request(url,headers={'User-Agent': AGENT}))
soup = BeautifulSoup(html, 'lxml')
for tag in soup.find_all(href=is_wikipedia):
print(' ' + tag['href'])
urls[shortname] = tag['href']
#break
time.sleep(1)
# write it back
with open(CSV, 'w', encoding='utf8') as f:
for shortname in sorted(urls.keys()):
f.write(shortname + ';' + urls[shortname] + '\n')
|
