def main():
browser = Browser()
try:
makedirs(DIRNAME)
except OSError:
pass
files = sorted(listdir(DIRNAME))
if files:
lastfile = files[-1]
else:
lastfile = "1989-04-16.gif"
lastday = lastfile.split(".")[0]
next_url = BASE_URL + lastday + "/"
while next_url:
html = browser.get_html(next_url)
img_url = re.search(r'''http://dilbert.com/dyn/str_strip.*?\.gif''', html).group(0)
filename = path.join(DIRNAME, next_url.split("/")[-2] + ".gif")
print filename
print "img:", img_url
with open(filename, "w") as file:
file.write(browser.get_html(img_url))
next_url = re.search(r'''href="(/strips/comic/.*?/") class="STR_Next PNG_Fix"''', html)
if next_url:
next_url = next_url.group(1)
else:
print html
def main():
browser = Browser()
next_url = "http://sinfest.net/archive_page.php?comicID=4323"
while next_url:
html = browser.get_html(next_url)
img_url = re.search(r'''http://sinfest.net/comikaze/comics/[\d-]*.gif''', html).group(0)
next_url = re.search(r'''"(http://sinfest.net/archive_page.php\?comicID=\d*)"><img src="images/next_a.gif"''', html)
if next_url:
next_url = next_url.group(1)
filename = img_url.split("/")[-1]
print filename
with open(filename, "w") as file:
file.write(browser.get_html(img_url))
print "img:", img_url
print "next:", next_url
def get_token(username, password=None, appid="616893704999769"):
url = ("""https://graph.facebook.com/oauth/authorize?client_id="""
+ appid + """&redirect_uri=http://www.facebook.com/connect/"""
"""login_success.html&type=user_agent&display=popup&scope="""
"user_about_me,friends_about_me,user_activities,friends_activities,"
"user_birthday,friends_birthday,user_checkins,friends_checkins,"
"user_education_history,friends_education_history,user_events,"
"friends_events,user_groups,friends_groups,user_hometown,friends_hometown,"
"user_interests,friends_interests,user_likes,friends_likes,user_location,"
"friends_location,user_notes,friends_notes,user_photos,friends_photos,"
"user_questions,friends_questions,user_relationships,"
"friends_relationships,user_relationship_details,"
"friends_relationship_details,user_religion_politics,"
"friends_religion_politics,user_status,friends_status,user_subscriptions,"
"friends_subscriptions,user_videos,friends_videos,user_website,"
"friends_website,user_work_history,friends_work_history,read_friendlists,"
"read_insights,read_mailbox,read_requests,read_stream,xmpp_login,"
"user_online_presence,friends_online_presence,ads_management,create_event,"
"manage_friendlists,manage_notifications,publish_actions,publish_stream,"
"rsvp_event,publish_actions,user_actions.music,friends_actions.music,"
"user_actions.news,friends_actions.news,user_actions.video,"
"friends_actions.video,user_games_activity,friends_games_activity,"
"manage_pages,email"
) # give me the power
if not password:
username, password = get_credentials(username)
browser = Browser()
form = browser.get_forms("http://fb.com")[0]
form["email"] = username
form["pass"] = password
form.submit()
assert troubleshoting(browser)
html = browser.get_html(url)
assert troubleshoting(browser)
html = browser.get_html()
if "Success" in html:
try:
utoken = next((url for url in reversed(browser.hist) if "token" in url))
except IndexError:
import IPython
IPython.embed()
token = utoken.split("=")[1]
token = token.split("&")[0]
return token
else:
browser.show()
raise ValueError("Not success")
#!/usr/bin/env python
#-*- coding: UTF-8 -*-
from litebrowser import Browser
from fileinput import input
import urllib
BASE_URL = ("http://translate.google.com/translate_a/t?"
"client=t&sl=auto&tl=es&hl=es-419&sc=2&ie=UTF-8&oe=UTF-8&"
"uptl=es&alttl=en&oc=1&otf=2&ssel=0&tsel=0&q=%s")
b = Browser()
b.go("http://translate.google.com")
for line in input():
text = urllib.quote(line)
b.go(BASE_URL % text)
print b.get_html()
def __init__(self, account):
self.account = account
self.browser = Browser()
class Claro:
def __init__(self, account):
self.account = account
self.browser = Browser()
def login(self):
form = self.browser.get_forms("https://individuos.claro.com.ar")[1]
form["login"] = self.account[0]
form["password"] = self.account[1]
form.submit()
def get_saldos(self):
saldos = {}
html = self.browser.get_html("web/guest/saldos-y-consumos1")
regexs = {
"Abono fijo": r'''
(?xs)Saldo\ del\ Abono:.*?\$
(?P<saldo> (?:\d+,)?\d+ ).*?Llevás\ consumidos\ \$
(?P<consumido> (?:\d+,)?\d+ ).*?
(?P<total> \d*,\d* ).*?Per.+?odo\ actual.*?
(?P<vencimiento> \d+/\d+/\d+ )
''',
"Paquete de datos": r'''
(?xs)Saldo\ de\ Paquetes.*?Te\ quedan\
(?P<saldo> \d+? )\ MB\ de\ tu\ paquete\ de\
(?P<total> \d+ )\ MB\..*?Vence\ el\
(?P<vencimiento> \d+/\d+/\d+ )
''',
"Paquete de sms": r'''
(?xs).*?Te\ quedan\
(?P<saldo> \d+ )\ SMS\ de\ tu\ paquete\ de\
(?P<total> \d+ )\ SMS\..*?Vence\ el\ +
(?P<vencimiento> \d+/\d+/\d+ )
''',
"SMS Promocionales": r'''
(?xs)SMS\ Promocionales.*?Tenés\ .*?
(?P<saldo> \d+ ).*?SMS\ disponibles\ hasta\ el\
(?P<vencimiento> \d+/\d+/\d+ )
''',
"Crédito prepago congelado": r'''
(?xs)Crédito\ de\ Recarga.*?Crédito\ Congelado.*?
Saldo.*?Vencimiento.*?\$
(?P<saldo> \d+,\d+ ).*?
(?P<vencimiento> \d+/\d+/\d+ ).*?Última\ recarga.*?
(?P<ultima_recarga> \d+/\d+/\d+ )
''',
"Crédito prepago vigente": r'''
(?xs)Crédito\ de\ Recarga.*?Recarga.*?\$
(?P<saldo> \d+,\d+ ).*?
(?P<vencimiento> \d+/\d+/\d+ )
''',
"Crédito prepago promocional": r'''
(?xs)Crédito\ de\ Recarga.*?Promocional.*?\$
(?P<saldo> \d+,\d+ ).*?
(?P<vencimiento> \d+/\d+/\d+ )
''',
"Crédito de recarga": r'''
(?xs)Crédito\ de\ Recarga.*?Última\ recarga.*?
(?P<ultima_recarga> \d+/\d+/\d+ )
'''
}
for title, regex in regexs.items():
match = re.search(regex, html)
if match:
saldos[title] = match.groupdict()
return saldos
def get_circulo_opciones(self):
self.browser.go("web/guest/consultar-claro-club")
self.browser.get_forms()[0].submit()
soup = BeautifulSoup(self.browser.get_html())
opciones = []
regex = re.compile(r"""(?xs) <tr>\ <td.*?>
(?P<descripcion>(?P<cantidad>\d+).*?) </td>\ <td.*?>
(?P<puntos>\d+) .*?</td>.*?goSubmit\('
(?P<codigo>\d+) '\)"""
)
for table in soup("table", {"class":"tabla tablaGris"}):
for row in table("tr"):
rawtext = row.__str__()
if "goSubmit(" in rawtext and "SMS" in rawtext:
match = regex.match(rawtext)
opciones.append(match.groupdict())
return opciones
