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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
|
#!/usr/bin/python3
# encoding=utf-8
#
# Copyright © 2018 Alexandre Detiste <alexandre@detiste.be>
# SPDX-License-Identifier: GPL-2.0-or-later
# Usage:
# curl -s -D headers.html \
# https://wiki.scummvm.org/index.php/Where_to_get_the_games > scummvm.html
# _build/run-tool-uninstalled tools/check_scummvm.py
import os
import re
from bs4 import BeautifulSoup
from game_data_packager.game import load_games
KEY = '22d200f8670dbdb3e253a90eee5098477c95c23d'
class Game:
gog: str | None = None
steam: int | None = None
def load_yaml() -> dict[str, Game]:
print('# Reading data from YAML...')
games = dict()
for name, game in load_games(
datadir=os.environ.get('GDP_BUILDDIR', 'out')
).items():
game.load_file_data()
if game.wikibase != 'https://wiki.scummvm.org/index.php/':
continue
assert game.wiki, name
g = Game()
for package in game.packages.values():
gog = package.gog or game.gog
steam = package.steam or game.steam
if 'game' in gog:
g.gog = gog['game']
elif 'url' in gog:
g.gog = gog['url']
if 'id' in steam:
g.steam = steam['id']
games[game.wiki] = g
return games
games = load_yaml()
# curl -s -D headers.html \
# https://wiki.scummvm.org/index.php/Where_to_get_the_games > scummvm.html
def load_html() -> dict[str, Game]:
print('# Reading data from ScummVM wiki...')
soup = BeautifulSoup(open("scummvm.html"), "html.parser")
downloads: dict[str, Game] = dict()
for table in soup.find_all('table', {'border': '1', 'width': '100%'}):
print('## ' + table.find_previous('span').text)
for row in table.find_all('tr'):
game = None
for link in row.find_all('a'):
url = link['href']
# URL that have been reviewed
if url == 'https://www.scummvm.org/games/':
continue
if url == 'https://www.msadams.com/downloads.htm':
continue
if 'cdaccess.com/' in url:
continue
if url.startswith('http://www.mdna-games.com'):
continue
m = re.search(r'/index.php\?title\=(.*?)$', url)
if m:
game = m.group(1)
downloads[game] = Game()
continue
m = re.search(r'https://www.gog.com/game/(.*?)\?pp\=%s' % KEY,
url)
if m:
if game is None:
print('Missing game id:', url)
continue
downloads[game].gog = m.group(1)
continue
m = re.search(r'http://store.steampowered.com/app/(.*?)$', url)
if m:
steam_id = int(m.group(1))
assert game is not None, url
downloads[game].steam = steam_id
continue
print(game, url)
return downloads
downloads = load_html()
print('# Join...')
no_game = Game()
for game, shop in sorted(games.items()):
new_gog = downloads.get(game, no_game).gog
if shop.gog != new_gog:
print("%-70s" % game, shop.gog, new_gog)
new_steam = downloads.get(game, no_game).steam
if shop.steam != new_steam:
print("%-70s" % game, shop.steam, new_steam)
|
