class ParolesmaniaBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'http://www.parolesmania.com/'
searchSong = URL('recherche.php\?c=title&k=(?P<pattern>[^/]*).*',
SearchSongPage)
searchArtist = URL('recherche.php\?c=artist&k=(?P<pattern>[^/]*).*',
SearchArtistPage)
songLyrics = URL(
'paroles_(?P<artistid>[^/]*)/paroles_(?P<songid>[^/]*)\.html',
LyricsPage)
artistSongs = URL('paroles_(?P<artistid>[^/]*)\.html', ArtistSongsPage)
def iter_lyrics(self, criteria, pattern):
if criteria == 'artist':
artist_ids = self.searchArtist.go(pattern=pattern).get_artist_ids()
it = []
# we just take the 3 first artists to avoid too many page loadings
for aid in artist_ids[:3]:
it = itertools.chain(
it,
self.artistSongs.go(artistid=aid).iter_lyrics())
return it
elif criteria == 'song':
return self.searchSong.go(pattern=pattern).iter_lyrics()
def get_lyrics(self, id):
ids = id.split('|')
try:
self.songLyrics.go(artistid=ids[0], songid=ids[1])
songlyrics = self.page.get_lyrics()
return songlyrics
except BrowserHTTPNotFound:
return
class LyricsdotcomBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'http://www.lyrics.com'
search = URL('/serp.php\?st=(?P<pattern>.*)&qtype=(?P<criteria>1|2)',
SearchPage)
songLyrics = URL('/lyric/(?P<id>\d*)', LyricsPage)
artistsong = URL('/artist/(?P<id>.*)', ArtistPages)
def iter_lyrics(self, criteria, pattern):
if criteria == 'song':
self.search.go(pattern=pattern, criteria=1)
assert self.search.is_here()
for song in self.page.iter_lyrics():
yield song
elif criteria == 'artist':
self.search.go(pattern=pattern, criteria=2)
assert self.search.is_here()
for artist in self.page.iter_artists():
for song in self.artistsong.go(id=artist.id).iter_lyrics():
yield song
def get_lyrics(self, id):
return self.songLyrics.go(id=id).get_lyrics()
class BECMBrowser(AbstractBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://www.becm.fr'
PARENT = 'creditmutuel'
login = URL('/fr/authentification.html', LoginPage)
advisor = URL('/fr/banques/Details.aspx\?banque=.*', AdvisorPage)
@need_login
def get_advisor(self):
advisor = None
if not self.is_new_website:
self.accounts.stay_or_go(subbank=self.currentSubBank)
if self.page.get_advisor_link():
advisor = self.page.get_advisor()
self.location(
self.page.get_advisor_link()).page.update_advisor(advisor)
else:
advisor = self.new_accounts.stay_or_go(
subbank=self.currentSubBank).get_advisor()
link = self.page.get_agency()
if link:
self.location(link)
self.page.update_advisor(advisor)
return iter([advisor]) if advisor else iter([])
class T411Browser(LoginBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://www.t411.ai/'
home = URL('$', HomePage)
search = URL(
'torrents/search/\?search=(?P<pattern>.*)&order=seeders&type=desc',
SearchPage)
# Order matters here: 'torrents/[^&]*' would match '/torrents/download/\?id...' and
# TorrentPage would crash on the bencode data, so DownloadPage must be listed before
# TorrentPage
download = URL('/torrents/download/\?id=(?P<id>.*)', DownloadPage)
torrent = URL('/torrents/details/\?id=(?P<id>.*)&r=1', 'torrents/[^&]*',
TorrentPage)
def do_login(self):
self.home.go()
if not self.page.logged:
self.page.login(self.username, self.password)
if not self.page.logged:
raise BrowserIncorrectPassword()
@need_login
def iter_torrents(self, pattern):
return self.search.go(pattern=pattern).iter_torrents()
@need_login
def get_torrent(self, fullid, torrent=None):
try:
self.torrent.go(id=fullid)
torrent = self.page.get_torrent()
return torrent
except BrowserHTTPNotFound:
return
class SGEnterpriseBrowser(SGPEBrowser):
BASEURL = 'https://entreprises.secure.societegenerale.fr'
LOGIN_FORM = 'auth'
MENUID = 'BANREL'
CERTHASH = '2231d5ddb97d2950d5e6fc4d986c23be4cd231c31ad530942343a8fdcc44bb99'
accounts = URL('/icd/syd-front/data/syd-comptes-accederDepuisMenu.json', AccountsJsonPage)
balances = URL('/icd/syd-front/data/syd-comptes-chargerSoldes.json', BalancesJsonPage)
history = URL('/icd/syd-front/data/syd-comptes-chargerReleve.json',
'/icd/syd-front/data/syd-intraday-chargerDetail.json', HistoryJsonPage)
history_next = URL('/icd/syd-front/data/syd-comptes-chargerProchainLotEcriture.json', HistoryJsonPage)
profile = URL('/gae/afficherModificationMesDonnees.html', ProfileEntPage)
def go_accounts(self):
self.accounts.go()
@need_login
def get_accounts_list(self):
accounts = []
accounts.extend(self.accounts.stay_or_go().iter_accounts())
for acc in self.balances.go().populate_balances(accounts):
yield acc
@need_login
def iter_history(self, account):
value = self.history.go(data={'cl500_compte': account._id, 'cl200_typeReleve': 'valeur'}).get_value()
transactions = []
transactions.extend(self.history.go(data={'cl500_compte': account._id, 'cl200_typeReleve': value}).iter_history(value=value))
transactions.extend(self.location('/icd/syd-front/data/syd-intraday-chargerDetail.json', data={'cl500_compte': account._id}).page.iter_history())
return iter(transactions)
class IlmatieteenlaitosBrowser(PagesBrowser):
BASEURL = 'http://ilmatieteenlaitos.fi'
cities = URL(
'/etusivu\?p_p_id=locationmenuportlet_WAR_fmiwwwweatherportlets&p_p_lifecycle=2&p_p_state=normal&'
'p_p_mode=view&p_p_cacheability=cacheLevelFull&term=(?P<pattern>.*)',
SearchCitiesPage)
weather_query = URL(
'/paikallissaa\?p_p_id=locationmenuportlet_WAR_fmiwwwweatherportlets&p_p_lifecycle=1&'
'p_p_state=normal&p_p_mode=view&_locationmenuportlet_WAR_fmiwwwweatherportlets_action='
'changelocation')
weather = URL('/saa/(?P<city_url>.*)', WeatherPage)
observations = URL('/observation-data\?station=(?P<station_id>.*)',
ObservationsPage)
def iter_city_search(self, pattern):
return self.cities.go(pattern=pattern).iter_cities()
def iter_forecast(self, city):
return self.weather_query.go(data={
"place": city.name,
"forecast": "short"
}).iter_forecast()
def get_current(self, city):
station_id = self.weather_query.go(data={
"place": city.name,
"forecast": "short"
}).get_station_id()
return self.observations.go(station_id=station_id).get_current()
class T411Browser(LoginBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://www.t411.in/'
home = URL('$', HomePage)
search = URL(
'torrents/search/\?search=(?P<pattern>.*)&order=seeders&type=desc',
SearchPage)
torrent = URL('/torrents/details/\?id=(?P<id>.*)&r=1', 'torrents/[^&]*',
TorrentPage)
#def __init__(self, *args, **kwargs):
# Browser.__init__(self, *args, **kwargs)
def do_login(self):
self.home.go()
if not self.page.logged:
self.page.login(self.username, self.password)
if not self.page.logged:
raise BrowserIncorrectPassword()
@need_login
def iter_torrents(self, pattern):
return self.search.go(pattern=pattern).iter_torrents()
@need_login
def get_torrent(self, fullid, torrent=None):
try:
self.torrent.go(id=fullid)
torrent = self.page.get_torrent()
return torrent
except BrowserHTTPNotFound:
return
class BtmonBrowser(PagesBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'http://www.btmon.com/'
home = URL('$', HomePage)
search = URL(r'/torrent/\?sort=relevance&f=(?P<pattern>.*)', SearchPage)
torrent = URL(r'/(?P<torrent_id>.*)\.torrent\.html', TorrentPage)
def get_bpc_cookie(self):
if 'BPC' not in self.session.cookies:
self.home.go()
bpcCookie = str(self.page.content).split('BPC=')[-1].split('"')[0]
self.session.cookies['BPC'] = bpcCookie
def iter_torrents(self, pattern):
self.get_bpc_cookie()
return self.search.go(pattern=pattern).iter_torrents()
def get_torrent(self, id):
try:
self.get_bpc_cookie()
self.torrent.go(torrent_id=id)
torrent = self.page.get_torrent()
return torrent
except BrowserHTTPNotFound:
return
class LyricsplanetBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'http://www.lyricsplanet.com/'
home = URL('$', HomePage)
search = URL('search\.php$', SearchPage)
artist = URL('search\.php\?field=artisttitle&value=(?P<artistid>[^/]*)$',
ArtistPage)
lyrics = URL('lyrics\.php\?id=(?P<songid>[^/]*)$', LyricsPage)
def iter_lyrics(self, criteria, pattern):
self.home.stay_or_go()
assert self.home.is_here()
self.page.search_lyrics(criteria, pattern)
assert self.search.is_here()
if criteria == 'song':
return self.page.iter_song_lyrics()
elif criteria == 'artist':
artist_ids = self.page.get_artist_ids()
it = []
# we just take the 3 first artists to avoid too many page loadings
for aid in artist_ids[:3]:
it = itertools.chain(
it,
self.artist.go(artistid=aid).iter_lyrics())
return it
def get_lyrics(self, id):
try:
self.lyrics.go(songid=id)
songlyrics = self.page.get_lyrics()
return songlyrics
except BrowserHTTPNotFound:
return
class SGPEBrowser(LoginBrowser):
login = URL('$', LoginPage)
cards = URL('/Pgn/.+PageID=Cartes&.+', CardsPage)
cards_history = URL('/Pgn/.+PageID=ReleveCarte&.+', CardHistoryPage)
def is_logged(self):
if not self.page or self.login.is_here():
return False
error = self.page.get_error()
if error is None:
return True
return False
def do_login(self):
assert isinstance(self.username, basestring)
assert isinstance(self.password, basestring)
if not self.password.isdigit():
raise BrowserIncorrectPassword('Password must be 6 digits long.')
self.login.stay_or_go()
self.session.cookies.set('PILOTE_OOBA', 'true')
self.page.login(self.username, self.password)
# force page change
if not self.accounts.is_here():
self.go_accounts()
if not self.is_logged():
raise BrowserIncorrectPassword()
def card_history(self, account, coming):
page = 1
while page:
self.location('/Pgn/NavigationServlet?PageID=ReleveCarte&MenuID=%sOPF&Classeur=1&Rib=%s&Carte=%s&Date=%s&PageDetail=%s&Devise=%s' % \
(self.MENUID, account.id, coming['carte'], coming['date'], page, account.currency))
for transaction in self.page.iter_transactions(
date=coming['date']):
yield transaction
if self.page.has_next():
page += 1
else:
page = False
@need_login
def get_cb_operations(self, account):
self.location(
'/Pgn/NavigationServlet?PageID=Cartes&MenuID=%sOPF&Classeur=1&NumeroPage=1&Rib=%s&Devise=%s'
% (self.MENUID, account.id, account.currency))
for coming in self.page.get_coming_list():
for tr in self.card_history(account, coming):
yield tr
def iter_investment(self, account):
raise NotImplementedError()
class IpinfodbBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'https://ipinfodb.com/'
home = URL('$', HomePage)
search = URL('ip_locator.php', LocationPage)
def get_location(self, ipaddr):
try:
self.home.go()
self.page.search(ipaddr)
iploc = self.page.get_location()
return iploc
except BrowserHTTPNotFound:
return
class SGProfessionalBrowser(SGEnterpriseBrowser):
BASEURL = 'https://professionnels.secure.societegenerale.fr'
LOGIN_FORM = 'auth_reco'
MENUID = 'SBOREL'
CERTHASH = '9f5232c9b2283814976608bfd5bba9d8030247f44c8493d8d205e574ea75148e'
profile = URL('/gao/modifier-donnees-perso-saisie.html', ProfileProPage)
class BECMBrowser(AbstractBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://www.becm.fr'
PARENT = 'creditmutuel'
login = URL('/fr/authentification.html', LoginPage)
advisor = URL('/fr/banques/Details.aspx\?banque=.*', AdvisorPage)
def do_login(self):
# Clear cookies.
self.do_logout()
self.login.go()
if not self.page.logged:
self.page.login(self.username, self.password)
# Many "Credit Mutuel" customers tried to add their connection to BECM, but the BECM
# website does not return any error when you try to login with correct Crédit Mutuel
# credentials, therefore we must suggest them to try regular Crédit Mutuel if login fails.
if self.login.is_here():
raise ActionNeeded(
"La connexion au site de BECM n'a pas fonctionné avec les identifiants fournis.\
Si vous êtes client du Crédit Mutuel, veuillez réessayer en sélectionnant le module Crédit Mutuel."
)
if self.verify_pass.is_here():
raise AuthMethodNotImplemented(
"L'identification renforcée avec la carte n'est pas supportée."
)
@need_login
def get_advisor(self):
advisor = None
if not self.is_new_website:
self.accounts.stay_or_go(subbank=self.currentSubBank)
if self.page.get_advisor_link():
advisor = self.page.get_advisor()
self.location(
self.page.get_advisor_link()).page.update_advisor(advisor)
else:
advisor = self.new_accounts.stay_or_go(
subbank=self.currentSubBank).get_advisor()
link = self.page.get_agency()
if link:
self.location(link)
self.page.update_advisor(advisor)
return iter([advisor]) if advisor else iter([])
class LimetorrentsBrowser(PagesBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://www.limetorrents.info/'
search = URL(r'/search/all/(?P<pattern>.*)/seeds/(?P<page>[0-9]+)/', SearchPage)
torrent = URL(r'/(?P<torrent_name>.*)-torrent-(?P<torrent_id>[0-9]+)\.html', TorrentPage)
def iter_torrents(self, pattern):
return self.search.go(pattern=pattern, page=1).iter_torrents()
def get_torrent(self, id):
try:
self.torrent.go(torrent_id=id, torrent_name='whatever')
torrent = self.page.get_torrent()
return torrent
except BrowserHTTPNotFound:
return
class CICBrowser(AbstractBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://www.cic.fr'
PARENT = 'creditmutuel'
login = URL(r'/fr/authentification.html',
r'/sb/fr/banques/particuliers/index.html',
r'/(?P<subbank>.*)/fr/$',
r'/(?P<subbank>.*)/fr/banques/accueil.html',
r'/(?P<subbank>.*)/fr/banques/particuliers/index.html',
LoginPage)
por = URL(r'/(?P<subbank>.*)fr/banque/PORT_Synthese.aspx', PorPage)
decoupled_state = URL(r'/fr/otp/SOSD_OTP_GetTransactionState.htm',
DecoupledStatePage)
cancel_decoupled = URL(r'/fr/otp/SOSD_OTP_CancelTransaction.htm',
CancelDecoupled)
class IpinfodbBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'https://ipinfodb.com/'
home = URL('$', LocationPage)
def get_location(self, ipaddr):
self.home.go(data={'ip': ipaddr})
return self.page.get_location()
class CpasbienBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'http://www.cpasbien.cm/'
search = URL('recherche/(?P<pattern>.*).html,trie-seeds-d', SearchPage)
torrent = URL('dl-torrent/(?P<id>.*)\.html', TorrentPage)
def iter_torrents(self, pattern):
self.search.go(pattern=pattern)
return self.page.iter_torrents()
def get_torrent(self, fullid):
try:
self.torrent.go(id=fullid)
torrent = self.page.get_torrent()
return torrent
except BrowserHTTPNotFound:
return
class NewspaperLibeBrowser(AbstractBrowser):
"NewspaperLibeBrowser class"
PARENT = 'genericnewspaper'
BASEURL = ''
article = URL('http://.*liberation.fr/.*', ArticlePage)
def __init__(self, weboob, *args, **kwargs):
self.weboob = weboob
super(self.__class__, self).__init__(*args, **kwargs)
class NewspaperTazBrowser(AbstractBrowser):
"NewspaperTazBrowser class"
PARENT = 'genericnewspaper'
BASEURL = 'http://www.taz.de'
article_page = URL('/.*', ArticlePage)
def __init__(self, *args, **kwargs):
self.weboob = kwargs['weboob']
super(NewspaperTazBrowser, self).__init__(*args, **kwargs)
class T411Browser(LoginBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://www.t411.si/'
home = URL('$', HomePage)
login = URL('/login$', LoginPage)
search = URL(r'/torrents/search/\?search=(?P<pattern>.*)', SearchPage)
download = URL(
'/telecharger-torrent/(?P<torrent_hash>[0-9a-f]{40})/(?P<torrent_name>\w+)',
DownloadPage)
torrent = URL('/torrents/(?P<torrent_id>[0-9]+)/(?P<torrent_name>.*)',
TorrentPage)
def do_login(self):
self.home.go()
if not self.page.logged:
self.page.login(self.username, self.password)
self.home.go()
if not self.page.logged:
raise BrowserIncorrectPassword()
@need_login
def iter_torrents(self, pattern):
return self.search.go(pattern=pattern).iter_torrents()
@need_login
def get_torrent(self, torrent):
try:
self.torrent.go(torrent_id=torrent.id, torrent_name=torrent.name)
torrent = self.page.get_torrent()
return torrent
except BrowserHTTPNotFound:
return
def get_torrent_file(self, torrent):
torrent = self.browser.get_torrent(torrent)
if not torrent:
return None
resp = self.browser.open(torrent.url)
return resp.content
class NewspaperInrocksBrowser(AbstractBrowser):
"NewspaperInrocksBrowser class"
PARENT = 'genericnewspaper'
BASEURL = 'http://www.lesinrocks.com'
article = URL('/\?p=.+', '/\d{4}/\d{2}/\d{2}/actualite/.*',
'http://blogs.lesinrocks.com/.*', '/.*', ArticlePage)
def __init__(self, *args, **kwargs):
self.weboob = kwargs['weboob']
super(NewspaperInrocksBrowser, self).__init__(*args, **kwargs)
class CICBrowser(AbstractBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://www.cic.fr'
PARENT = 'creditmutuel'
login = URL('/sb/fr/banques/particuliers/index.html',
'/(?P<subbank>.*)/fr/$',
'/(?P<subbank>.*)/fr/banques/accueil.html',
'/(?P<subbank>.*)/fr/banques/particuliers/index.html',
LoginPage)
class AmericanExpressLoginBrowser(SeleniumBrowser):
BASEURL = 'https://global.americanexpress.com'
DRIVER = webdriver.Chrome
# True for Production / False for debug
HEADLESS = True
login = URL(r'/login', LoginPage)
login_error = URL(r'/login', r'/authentication/recovery/password',
LoginErrorPage)
dashboard = URL(r'/dashboard', DashboardPage)
def __init__(self, config, *args, **kwargs):
super(AmericanExpressLoginBrowser, self).__init__(*args, **kwargs)
self.username = config['login'].get()
self.password = config['password'].get()
def do_login(self):
self.login.go()
self.wait_until_is_here(self.login)
self.page.login(self.username, self.password)
self.wait_until(
AnyCondition(
IsHereCondition(self.login_error),
IsHereCondition(self.dashboard),
))
if self.login_error.is_here():
error = self.page.get_error()
if any((
'The User ID or Password is incorrect' in error,
'Both the User ID and Password are required' in error,
)):
raise BrowserIncorrectPassword(error)
if 'Your account has been locked' in error:
raise ActionNeeded(error)
assert False, 'Unhandled error : "%s"' % error
class ParolesmusiqueBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'http://www.paroles-musique.com/'
home = URL('$',
HomePage)
songResults = URL('lyrics-paroles-0-.*,0.php',
SongResultsPage)
artistResults = URL('lyrics-paroles-.*-0,0.php',
ArtistResultsPage)
songLyrics = URL('paroles-(?P<songid>.*,p[0-9]*)',
SonglyricsPage)
artistSongs = URL('paroles-(?P<artistid>.*,a[0-9]*)',
ArtistSongsPage)
def iter_lyrics(self, criteria, pattern):
self.home.stay_or_go()
assert self.home.is_here()
self.page.search_lyrics(criteria, pattern)
if criteria == 'song':
assert self.songResults.is_here()
return self.page.iter_lyrics()
elif criteria == 'artist':
assert self.artistResults.is_here()
artist_ids = self.page.get_artist_ids()
it = []
# we just take the 3 first artists to avoid too many page loadings
for aid in artist_ids[:3]:
it = itertools.chain(it, self.artistSongs.go(artistid=aid).iter_lyrics())
return it
def get_lyrics(self, id):
try:
self.songLyrics.go(songid=id)
songlyrics = self.page.get_lyrics()
return songlyrics
except BrowserHTTPNotFound:
return
class KickassBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'https://kat.cr/'
search = URL('usearch/(?P<pattern>.*)/\?field=seeders&sorder=desc',
SearchPage)
torrent = URL('torrent-t(?P<id>.*).html', '.*-t[0-9]*\.html', TorrentPage)
def iter_torrents(self, pattern):
self.search.go(pattern=pattern)
#print( self.page.content)
return self.page.iter_torrents()
def get_torrent(self, fullid):
try:
self.torrent.go(id=fullid)
torrent = self.page.get_torrent()
return torrent
except BrowserHTTPNotFound:
return
class YggtorrentBrowser(LoginBrowser):
PROFILE = Wget()
TIMEOUT = 30
BASEURL = 'https://yggtorrent.to/'
home = URL('$', HomePage)
login = URL('/user/login$', LoginPage)
search = URL(r'/engine/search\?name=(?P<pattern>.*)&order=desc&sort=seed&do=search', SearchPage)
download = URL('/engine/download_torrent\?id=(?P<torrent_id>[0-9]+)', DownloadPage)
torrent = URL('/torrent/(?P<torrent_cat>.+)/(?P<torrent_subcat>.+)/(?P<torrent_id>[0-9]+)-(?P<torrent_name>.*)', TorrentPage)
def do_login(self):
self.home.go()
if not self.page.logged:
self.page.login(self.username, self.password)
self.home.go()
if not self.page.logged:
raise BrowserIncorrectPassword()
@need_login
def iter_torrents(self, pattern):
return self.search.go(pattern=pattern).iter_torrents()
@need_login
def get_torrent(self, id):
try:
self.torrent.go(torrent_id=id, torrent_name='anything', torrent_cat='any', torrent_subcat='thing')
torrent = self.page.get_torrent()
return torrent
except BrowserHTTPNotFound:
return
@need_login
def get_torrent_file(self, id):
torrent = self.browser.get_torrent(id)
if not torrent:
return None
resp = self.browser.open(torrent.url)
return resp.content
class PastealaconBrowser(PagesBrowser):
BASEURL = 'http://paste.alacon.org/'
paste = URL(r'(?P<id>\d+)', PastePage)
captcha = URL(r'%s' % re.escape('pastebin.php?captcha=1'), CaptchaPage)
raw = URL(r'%s(?P<id>\d+)' % re.escape('pastebin.php?dl='))
post = URL(r'$', PostPage)
@paste.id2url
def get_paste(self, url):
url = self.absurl(url, base=True)
m = self.paste.match(url)
if m:
return PastealaconPaste(m.groupdict()['id'])
def fill_paste(self, paste):
"""
Get as much as information possible from the paste page
"""
self.paste.stay_or_go(id=paste.id)
return self.page.fill_paste(paste)
def get_contents(self, _id):
"""
Get the contents from the raw URL
This is the fastest and safest method if you only want the content.
Returns unicode.
"""
try:
# despite what the HTTP header says, it is iso8859
return self.raw.open(id=_id).content.decode('iso8859-15')
except BrowserHTTPNotFound:
raise PasteNotFound()
def post_paste(self, paste, expiration=None):
self.post.stay_or_go().post(paste, expiration=expiration)
if self.captcha.is_here():
raise Spam()
self.page.fill_paste(paste)
class LyricsmodeBrowser(PagesBrowser):
PROFILE = Firefox()
TIMEOUT = 30
BASEURL = 'http://www.lyricsmode.com/'
search = URL('search\.php\?search=(?P<pattern>[^&/]*)$',
SearchPage)
songLyrics = URL('lyrics/(?P<letterid>[^/]*)/(?P<artistid>[^/]*)/(?P<songid>[^/]*)\.html$',
LyricsPage)
def iter_lyrics(self, criteria, pattern):
return self.search.go(pattern=pattern).iter_lyrics()
def get_lyrics(self, id):
subid = id.split('|')
try:
self.songLyrics.go(letterid=subid[0], artistid=subid[1], songid=subid[2])
songlyrics = self.page.get_lyrics()
return songlyrics
except BrowserHTTPNotFound:
return
class NewspaperFigaroBrowser(AbstractBrowser):
"NewspaperFigaroBrowser class"
PARENT = 'genericnewspaper'
BASEURL = 'http://lefigaro.fr'
article_page = URL(
'http://lefigaro.fr/(.*)/(\d{4})/(\d{2})/(\d{2})/(.*$)',
'http://\w+.lefigaro.fr/(.*)/(\d{4})/(\d{2})/(\d{2})/(.*$)',
'http://\w+.lefigaro.fr/(.*)', ArticlePage)
def __init__(self, weboob, *args, **kwargs):
self.weboob = weboob
super(self.__class__, self).__init__(*args, **kwargs)
class SprungeBrowser(PagesBrowser):
BASEURL = 'http://sprunge.us/'
paste = URL(r'(?P<id>\w+)', PastePage)
post = URL(r'$')
@paste.id2url
def get_paste(self, url):
url = self.absurl(url, base=True)
m = self.paste.match(url)
if m:
return SprungePaste(m.groupdict()['id'])
def fill_paste(self, paste):
"""
Get as much as information possible from the paste page
"""
return self.paste.stay_or_go(id=paste.id).fill_paste(paste)
def post_paste(self, paste):
url = self.post.open(data={'sprunge': paste.contents}).text.strip()
self.location(url)
return self.page.fill_paste(paste)