def get_game_datas(game_id, title):
gamedata = {
'title': "",
'genre': "",
'release': "",
'studio': "",
'plot': ""
}
try:
gamedata["title"] = title
f = urllib.urlopen('http://www.mobygames.com' + game_id)
page = f.read().replace('\r\n', '').replace('\n', '')
game_genre = re.findall('<a href="/genre/(.*?)">(.*?)</a>', page)
if game_genre:
gamedata["genre"] = scrapers.format_html_codes(game_genre[0][1])
game_release = re.findall('/release-info">(.*?)</a>', page)
if game_release:
gamedata["release"] = game_release[1][-4:]
game_studio = re.findall('Developed by(.*?)<a href="(.*?)">(.*?)</a>', page)
if game_studio:
gamedata["studio"] = scrapers.format_html_codes(game_studio[0][2])
game_plot = re.findall('Description</h2>(.*?)<div class', page)
if game_plot:
p = re.compile(r'<.*?>')
gamedata["plot"] = scrapers.format_html_codes(p.sub('', game_plot[0]))
return scrapers.format_html_codes(gamedata)
except:
return gamedata
def get_game_datas(game_id, title):
gamedata = {
'title': "",
'genre': "",
'release': "",
'studio': "",
'plot': ""
}
try:
gamedata["title"] = title
f = urllib.urlopen("http://thegamesdb.net/api/GetGame.php?id=" + game_id)
page = f.read().replace('\n', '')
game_genre = ' / '.join(re.findall('<genre>(.*?)</genre>', page))
if game_genre:
gamedata["genre"] = scrapers.format_html_codes(game_genre)
game_release = ''.join(re.findall('<ReleaseDate>(.*?)</ReleaseDate>', page))
if game_release:
gamedata["release"] = scrapers.format_html_codes(game_release[-4:])
game_studio = ''.join(re.findall('<Developer>(.*?)</Developer>', page))
if game_studio:
gamedata["studio"] = scrapers.format_html_codes(game_studio)
game_plot = ''.join(re.findall('<Overview>(.*?)</Overview>', page))
if game_plot:
gamedata["plot"] = scrapers.format_html_codes(game_plot)
return gamedata
except:
return None
def get_games_by_name(search):
results = []
try:
f = urllib.urlopen('http://www.mobygames.com/search/quick?q=' + search.replace(' ', '+') + '&sFilter=1&sG=on')
for line in f.readlines():
if 'searchNumber' in line:
split_games = re.findall('Game: (.*?)</span></div>', line)
for games in split_games:
game_title = re.findall('<a href="(.*?)">(.*?)</a>', games)
split_versions = re.findall('nowrap"><a href="(.*?)">(.*?)</a> ', games)
if split_versions:
for version in split_versions:
game = {}
game["title"] = scrapers.format_html_codes(game_title[0][1])
game["id"] = 'http://www.mobygames.com' + version[0]
game["system"] = version[1]
results.append(game)
else:
game = {}
game["title"] = scrapers.format_html_codes(game_title[0][1].replace('&', '&').replace(''', "'"))
one_version = re.findall('nowrap">(.*?) \(', games)
game["id"] = 'http://www.mobygames.com' + game_title[0][0]
game["system"] = one_version[0]
results.append(game)
return results
except:
return results
def get_games_with_system(search, system):
scraper_sysid = __scrapermap__[system]
results = []
try:
f = urllib.urlopen('http://www.mobygames.com/search/quick?q=' + search.replace(' ', '+')
+ '&p=' + scraper_sysid + '&sFilter=1&sG=on')
for line in f.readlines():
if 'searchNumber' in line:
split_games = re.findall('Game: (.*?)</span></div>', line)
for games in split_games:
game_title = re.findall('<a href="(.*?)">(.*?)</a>', games)
split_versions = re.findall('nowrap"><a href="(.*?)">(.*?)</a> ', games)
if split_versions:
for version in split_versions:
game = {}
game["title"] = scrapers.format_html_codes(game_title[0][1])
game["id"] = 'http://www.mobygames.com' + version[0]
game["system"] = system
results.append(game)
else:
game = {}
game["title"] = scrapers.format_html_codes(game_title[0][1])
game["id"] = game_title[0][0]
game["system"] = system
results.append(game)
return results
except:
return results
def get_game_datas(game_id, title):
gamedata = {
'title': "",
'genre': "",
'release': "",
'studio': "",
'plot': ""
}
try:
gamedata["title"] = title
f = urllib.urlopen("http://www.gamefaqs.com/" + str(game_id))
page = f.read().replace('\r\n', '')
game_genre = re.findall(r'</a> » <a href="(.*?)">(.*?)</a> » <a href="/', page)
if game_genre:
gamedata["genre"] = game_genre[0][1]
game_release = re.findall(r'Release: <a href="(.*?)">(.*?) »</a>', page)
if game_release:
gamedata["release"] = game_release[0][1][-4:]
game_studio = re.findall(r'<ul><li><a href="/features/company/(.*?)">(.*?)</a></li>', page)
if game_studio:
p = re.compile(r'<.*?>')
gamedata["studio"] = p.sub('', game_studio[0][1])
game_plot = re.findall(r'Description</h2></div><div class="body"><div class="details">(.*?)</div></div>', page)
if game_plot:
gamedata["plot"] = scrapers.format_html_codes(game_plot[0])
return gamedata
except:
return gamedata
def get_game_datas(game_id, title):
gamedata = {
'title': "",
'genre': "",
'release': "",
'studio': "",
'plot': ""
}
try:
gamedata["title"] = title
f = urllib.urlopen('http://www.allgame.com/game.php?id=' + game_id)
page = str(f.readlines())
game_genre = ''.join(re.findall('<a href="genre.php[^>]*>(.*?)</a>', page))
if game_genre:
gamedata["genre"] = game_genre
release_date = re.findall('<h3>Release Date</h3>[^>]*>(.*?)</p>', page)
if release_date:
gamedata["release"] = release_date[0][-4:]
game_studio = re.findall('<h3>Developer</h3>[^>]*>(.*?)</p>', page)
if game_studio:
p = re.compile(r'<.*?>')
gamestudio = p.sub('', game_studio[0])
if gamestudio:
gamedata["studio"] = gamestudio.rstrip()
plot = re.findall('<h2[^>]*>(.*?)</p>(.*?)<p>(.*?)</p>', page)
if plot:
p = re.compile(r'<.*?>')
gamedata["plot"] = scraperutils.format_html_codes(p.sub('', plot[0][2]))
return gamedata
except:
return gamedata
def get_games_with_system(search, system):
scraper_sysid = __scrapermap__[system]
results = []
try:
f = urllib.urlopen('http://www.gamefaqs.com/search/index.html?platform={0}&game={1}'
.format(scraper_sysid, search.replace(' ', '+')))
gets = re.findall(r'\s+?<a href="(.*?)"\s+?>(.*?)</a></td>', f.read().replace('\r\n', ''))
for get in gets:
game = {}
game["id"] = get[0].split('/')[2].split('-')[0]
game["title"] = scrapers.format_html_codes(get[1])
game["system"] = system
results.append(game)
return results
except:
return results
def get_games_by_name(search):
results = []
try:
f = urllib.urlopen('http://www.gamefaqs.com/search/index.html?platform=0&game=' + search.replace(' ', '+'))
gets = {}
gets = re.findall(r'\s+?<a href="(.*?)"\s+?>(.*?)</a></td>', f.read().replace('\r\n', ''))
for get in gets:
game = {}
system = get[0].split('/')
game["id"] = get[0].split('/')[2].split('-')[0]
game["title"] = scrapers.format_html_codes(get[1])
game["system"] = system[1].upper()
results.append(game)
return results
except:
return results
def get_games_with_system(game_name, system):
scraper_sysid = __scrapermap__[system]
params = urllib.urlencode({'sql': game_name, 'opt1': 81})
results = []
try:
f = urllib.urlopen('http://www.allgame.com/search.php', params)
for line in f.readlines():
if '"game.php?id=' in line:
game = {}
game["id"] = ''.join(re.findall('<a[^>]*id=(.*?)">', line))
game["title"] = scraperutils.format_html_codes(''.join(re.findall('<a[^>]*>(.*?)</a>', line)))
if '"platform.php?id=' in line:
game["system"] = ''.join(re.findall('<a[^>]*>(.*?)</a>', line))
if game["system"].lower() == scraper_sysid.lower():
game["system"] = system
results.append(game)
return results
except:
return results