def test_cookies(self):
import urllib2
# this test page depends on cookies, and an http-equiv refresh
#cj = CreateBSDDBCookieJar("/home/john/db.db")
cj = CookieJar()
handlers = [
HTTPCookieProcessor(cj),
HTTPRefreshProcessor(max_time=None, honor_time=False),
HTTPEquivProcessor(),
HTTPRedirectHandler(), # needed for Refresh handling in 2.4.0
# HTTPHandler(True),
# HTTPRedirectDebugProcessor(),
# HTTPResponseDebugProcessor(),
]
o = apply(build_opener, handlers)
try:
install_opener(o)
try:
r = urlopen(urljoin(self.uri, "/cgi-bin/cookietest.cgi"))
except urllib2.URLError, e:
#print e.read()
raise
data = r.read()
#print data
self.assert_(
data.find("Your browser supports cookies!") >= 0)
self.assert_(len(cj) == 1)
# test response.seek() (added by HTTPEquivProcessor)
r.seek(0)
samedata = r.read()
r.close()
self.assert_(samedata == data)
def _retrieve_product(cls, url):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [('User-agent', 'Mozilla/5.0 (MyProgram/0.1)'),
('From', '*****@*****.**')]
mechanize.install_opener(opener)
browser = mechanize.Browser()
product_data = browser.open(url).get_data()
soup = BeautifulSoup(product_data)
product_name = soup.find('h1').string.encode('ascii', 'ignore')
product_price = soup.find('span', {'id': 'product_price'})
product_price = Decimal(clean_price_string(product_price.string))
payment_methods = ['cash', 'deposit', 'wire_transfer']
additional_data = soup.find('td', 'descr').findAll('h3')
if not additional_data:
payment_methods.extend(['debit_card', 'credit_card'])
elif additional_data[0].string and 'Contado' not in \
additional_data[0].string:
payment_methods.extend(['debit_card', 'credit_card'])
prices = {}
for p in payment_methods:
prices[p] = product_price
return [product_name, prices]
def slurp_with_login_and_pwd():
import sys
import mechanize
# sys.path.append('ClientCookie-1.0.3')
# from mechanize import ClientCookie
# sys.path.append('ClientForm-0.1.17')
# import ClientForm
# Create special URL opener (for User-Agent) and cookieJar
cookieJar = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookieJar))
opener.addheaders = [("User-agent","Mozilla/5.0 (compatible)")]
mechanize.install_opener(opener)
fp = mechanize.urlopen("http://login.yahoo.com")
forms = mechanize.ParseResponse(fp)
fp.close()
# print forms on this page
for form in forms:
print "***************************"
print form
form = forms[0]
form["login"] = "******" # use your userid
form["passwd"] = "password" # use your password
fp = mechanize.urlopen(form.click())
fp.close()
fp = mechanize.urlopen("https://class.coursera.org/ml-003/lecture/download.mp4?lecture_id=1") # use your group
fp.readlines()
fp.close()
def _checkStoredInjections(self):
for r in self.results:
# At this state injections in Result obj are not
# compacted yet so it will only be 1st injected param
url, data = r.target.getPayloadedUrl(r.first_param, "")
# In case of proxy
if self.engine.getOption('http-proxy') is not None:
proxy = ProxyHandler({'http': self.engine.getOption('http-proxy')})
opener = build_opener(proxy)
install_opener(opener)
# Some headers
if self.engine.getOption('ua') is not None:
if self.engine.getOption('ua') is "RANDOM":
headers = {'User-Agent': random.choice(USER_AGENTS)}
else:
headers = {'User-Agent': self.engine.getOption('ua')}
else:
headers = {}
if self.engine.getOption("cookie") is not None:
headers["Cookie"] = self.engine.getOption("cookie")
# Build the request
req = Request(url, data, headers)
try:
to = 10 if self.engine.getOption('http-proxy') is None else 20
response = urlopen(req, timeout=to)
except HTTPError, e:
self._addError(e.code, r.target.getAbsoluteUrl())
continue
except URLError, e:
self._addError(e.reason, r.target.getAbsoluteUrl())
continue
def init(self):
br = mechanize.Browser()
br.set_handle_robots(False)
self.cj = mechanize.LWPCookieJar()
br.set_cookiejar(self.cj)
br.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(),
max_time=1)
br.open("https://www.tumblr.com/login")
br.select_form(nr=0)
br['user[email]'] = ""
br['user[password]'] = ""
url, data, hdrs = br.form.click_request_data()
br.open("https://www.tumblr.com/login", data)
self.nf = 0
opener = mechanize.build_opener(
mechanize.HTTPCookieProcessor(self.cj))
mechanize.install_opener(opener)
self._fetch()
def _performInjections(self, target):
# Check every parameter
for k, v in target.params.iteritems():
pl = Payload(taint=True)
url, data = target.getPayloadedUrl(k, pl.payload)
# In case of proxy
if self.engine.getOption('http-proxy') is not None:
proxy = ProxyHandler({'http': self.engine.getOption('http-proxy')})
opener = build_opener(proxy)
install_opener(opener)
# Some headers
if self.engine.getOption('ua') is not None:
if self.engine.getOption('ua') is "RANDOM":
headers = {'User-Agent': random.choice(USER_AGENTS)}
else:
headers = {'User-Agent': self.engine.getOption('ua')}
else:
headers = {}
if self.engine.getOption("cookie") is not None:
headers["Cookie"] = self.engine.getOption("cookie")
# Build the request
req = Request(url, data, headers)
try:
to = 10 if self.engine.getOption('http-proxy') is None else 20
response = urlopen(req, timeout=to)
except HTTPError, e:
self._addError(e.code, target.getAbsoluteUrl())
return
except URLError, e:
self._addError(e.reason, target.getAbsoluteUrl())
return
def readUrl(inUrl):
tryCount = 0
while tryCount < 5 :
# print "Create CookieJar"
cookies = mechanize.CookieJar()
# print "Build Opener"
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
# print "Add Headers"
opener.addheaders = [("User-agent", "Mozilla/5.0 (compatible; MyProgram/0.1)"),("From", "*****@*****.**")]
# print "Install Opener"
mechanize.install_opener(opener)
try:
# print "Open URL"
response = mechanize.urlopen(inUrl)
tryCount = 99
except:
tryCount += 1
print "******** Error on urlopen ***********"
print "URL: ", inUrl
print "Trying Again....", tryCount
# print response.read()
# html = urllib.urlopen(inUrl).read()
# print "Reading Response"
html = response.read()
# print "Response Read:", html[0:100]
root = lxml.html.fromstring(html)
# print "Root created: ", root
return root
def test_cookies(self):
import urllib2
# this test page depends on cookies, and an http-equiv refresh
#cj = CreateBSDDBCookieJar("/home/john/db.db")
cj = CookieJar()
handlers = [
HTTPCookieProcessor(cj),
HTTPRefreshProcessor(max_time=None, honor_time=False),
HTTPEquivProcessor(),
HTTPRedirectHandler(), # needed for Refresh handling in 2.4.0
# HTTPHandler(True),
# HTTPRedirectDebugProcessor(),
# HTTPResponseDebugProcessor(),
]
o = apply(build_opener, handlers)
try:
install_opener(o)
try:
r = urlopen(urljoin(self.uri, "/cgi-bin/cookietest.cgi"))
except urllib2.URLError, e:
#print e.read()
raise
data = r.read()
#print data
self.assert_(data.find("Your browser supports cookies!") >= 0)
self.assert_(len(cj) == 1)
# test response.seek() (added by HTTPEquivProcessor)
r.seek(0)
samedata = r.read()
r.close()
self.assert_(samedata == data)
def customizeUserAgent():
import mechanize
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
# Pretend to be Chrome to avoid getting the mobile site.
opener.addheaders = [("User-agent", "Chrome/16.0.912.63")]
mechanize.install_opener(opener)
def readUrl(inUrl):
tryCount = 0
while tryCount < 5:
# print "Create CookieJar"
cookies = mechanize.CookieJar()
# print "Build Opener"
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
# print "Add Headers"
opener.addheaders = [("User-agent",
"Mozilla/5.0 (compatible; MyProgram/0.1)"),
("From", "*****@*****.**")]
# print "Install Opener"
mechanize.install_opener(opener)
try:
# print "Open URL"
response = mechanize.urlopen(inUrl)
tryCount = 99
except:
tryCount += 1
print "******** Error on urlopen ***********"
print "URL: ", inUrl
print "Trying Again....", tryCount
# print response.read()
# html = urllib.urlopen(inUrl).read()
# print "Reading Response"
html = response.read()
# print "Response Read:", html[0:100]
root = lxml.html.fromstring(html)
# print "Root created: ", root
return root
def retrieve_product_data(self, product_link):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [('User-agent', 'Mozilla/5.0 (MyProgram/0.1)'),
('From', '*****@*****.**')]
mechanize.install_opener(opener)
browser = mechanize.Browser()
product_data = browser.open(product_link).get_data()
soup = BeautifulSoup(product_data)
product_name = soup.find('title').string.encode('ascii', 'ignore')
product_prices = soup.find('div', 'price').contents
try:
cash_price = int(clean_price_string(product_prices[4]))
product_data = ProductData()
product_data.custom_name = product_name
product_data.price = cash_price
product_data.url = product_link
product_data.comparison_field = product_link
return product_data
except IndexError:
return None
def retrieve_product_links(self):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [('User-agent', 'Mozilla/5.0 (MyProgram/0.1)'),
('From', '*****@*****.**')]
mechanize.install_opener(opener)
url_base = 'http://www.globalmac.cl/'
browser = mechanize.Browser()
url_extensions = [
['Distribuidor-Apple-Chile/MacBook-Air', 'Notebook'],
['Distribuidor-Apple-Chile/MacBook-Pro', 'Notebook'],
['Hardware-Mac-PC/Discos-Duros-Notebook-SATA-2.5', 'StorageDrive'],
['Hardware-Mac-PC/Discos-Duros-SATA-3.5', 'StorageDrive'],
['Hardware-Mac-PC/Discos-Duros-SSD-SATA-2.5', 'StorageDrive'],
]
product_links = []
for url_extension, ptype in url_extensions:
url = url_base + url_extension
base_data = browser.open(url).get_data()
soup = BeautifulSoup(base_data)
for item in soup.findAll('div', 'name'):
product_links.append([item.find('a')['href'], ptype])
return product_links
def slurp_with_login_and_pwd():
import sys
import mechanize
# sys.path.append('ClientCookie-1.0.3')
# from mechanize import ClientCookie
# sys.path.append('ClientForm-0.1.17')
# import ClientForm
# Create special URL opener (for User-Agent) and cookieJar
cookieJar = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookieJar))
opener.addheaders = [("User-agent", "Mozilla/5.0 (compatible)")]
mechanize.install_opener(opener)
fp = mechanize.urlopen("http://login.yahoo.com")
forms = mechanize.ParseResponse(fp)
fp.close()
# print forms on this page
for form in forms:
print "***************************"
print form
form = forms[0]
form["login"] = "******" # use your userid
form["passwd"] = "password" # use your password
fp = mechanize.urlopen(form.click())
fp.close()
fp = mechanize.urlopen(
"https://class.coursera.org/ml-003/lecture/download.mp4?lecture_id=1"
) # use your group
fp.readlines()
fp.close()
def retrieve_product_data(self, product_link):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [('User-agent', 'Mozilla/5.0 (MyProgram/0.1)'),
('From', '*****@*****.**')]
mechanize.install_opener(opener)
browser = mechanize.Browser()
product_data = browser.open(product_link).get_data()
soup = BeautifulSoup(product_data)
product_name = soup.find('title').string.encode('ascii', 'ignore')
product_prices = soup.find('div', 'price').contents
try:
cash_price = int(clean_price_string(product_prices[4]))
product_data = ProductData()
product_data.custom_name = product_name
product_data.price = cash_price
product_data.url = product_link
product_data.comparison_field = product_link
return product_data
except IndexError:
return None
def retrieve_product_links(self):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [('User-agent', 'Mozilla/5.0 (MyProgram/0.1)'),
('From', '*****@*****.**')]
mechanize.install_opener(opener)
url_base = 'http://www.globalmac.cl/'
browser = mechanize.Browser()
url_extensions = [
['Distribuidor-Apple-Chile/MacBook-Air', 'Notebook'],
['Distribuidor-Apple-Chile/MacBook-Pro', 'Notebook'],
['Hardware-Mac-PC/Discos-Duros-Notebook-SATA-2.5', 'StorageDrive'],
['Hardware-Mac-PC/Discos-Duros-SATA-3.5', 'StorageDrive'],
['Hardware-Mac-PC/Discos-Duros-SSD-SATA-2.5', 'StorageDrive'],
]
product_links = []
for url_extension, ptype in url_extensions:
url = url_base + url_extension
base_data = browser.open(url).get_data()
soup = BeautifulSoup(base_data)
for item in soup.findAll('div', 'name'):
product_links.append([item.find('a')['href'], ptype])
return product_links
def __init__(self, username="******", password="******"): self.username = "******"+username self.password = password self.password_manager = urllib2.HTTPPasswordMgrWithDefaultRealm() ntlm_auth = HTTPNtlmAuthHandler.HTTPNtlmAuthHandler(self.password_manager) opener = mechanize.build_opener(ntlm_auth) mechanize.install_opener(opener)
def GetHtml(url):
opener = mechanize.build_opener()
opener.addheaders = [("User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0) Gecko/20100101 Firefox/4.0")]
mechanize.install_opener(opener)
request = mechanize.urlopen(url)
html = request.read()
request.close()
return html
def themain():
#browser=mechanize.Browser()
#browser.open('http://www.baidu.com')
cj = mechanize.LWPCookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cj))
mechanize.install_opener(opener)
r = mechanize.urlopen('http://www.baidu.com')
cj.save('cookie.txt', ignore_discard=True, ignore_expires=True)
def __init__(self, username="******", password="******"):
self.username = "******" + username
self.password = password
self.password_manager = urllib2.HTTPPasswordMgrWithDefaultRealm()
ntlm_auth = HTTPNtlmAuthHandler.HTTPNtlmAuthHandler(
self.password_manager)
opener = mechanize.build_opener(ntlm_auth)
mechanize.install_opener(opener)
def setup_mechanize():
"""
Set up user agent for all mechanize calls.
"""
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
homepage = "http://github.com/aszlig/picfetcher"
opener.addheaders = [("User-agent", "PicFetcher/0.1.0 (+%s)" % homepage)]
mechanize.install_opener(opener)
def openUrl(url, cookie=None, login=False):
"""
Opens a given url through mechanize.
If there is no cookie (string path) passed in or if there is a cooke path
passed in but the login parameter is False (signifying to open the url with
cookie saved in the cookie path), the html from the opened url is returned
as a string.
If a cookie path is passed in and the login parameter is True, then the
Mechanize.Broswer object is returned to perform a yogaglo login through
a form submission.
"""
browser = mechanize.Browser()
browser.addheaders = [
('User-Agent',
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:24.0) Gecko/20100101 Firefox/24.0'),
('Accept',
'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'),
('Accept-Language', 'en-gb,en;q=0.5'),
('Accept-Charset', 'ISO-8859-1,utf-8;q=0.7,*;q=0.7'),
('Keep-Alive', '115'),
('Connection', 'keep-alive'),
('Cache-Control', 'max-age=0'),
]
#Experimental?
# browser.set_handle_gzip(True)
browser.set_handle_redirect(True)
browser.set_handle_referer(True)
browser.set_handle_robots(False)
browser.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time = 1)
if not cookie is None:
cj = cookielib.LWPCookieJar()
browser.set_cookiejar(cj)
opener = mechanize.build_opener(HTTPCookieProcessor(cj))
mechanize.install_opener(opener)
# trying to login, no cookie, must return browser so it can follow the
# login url
if login is True:
browser.open(url)
return browser
# can't set to expire, can't read when this particular cookie expires
cj.load(cookie , ignore_discard=True)
return browser.open(url).read()
def initialize_browser():
"""Configurações para contornar os cookies, robots.txt e outros para fingir ser um browser normal."""
cookiejar = cookielib.LWPCookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookiejar))
mechanize.install_opener(opener)
browser = mechanize.Browser()
browser.set_handle_robots(False)
browser.set_handle_redirect(True)
browser.set_cookiejar(cookiejar)
browser.set_handle_equiv(True)
browser.set_handle_referer(True)
browser.set_handle_refresh(mechanize._http.HTTPRefreshProcessor(), max_time=2)
browser.addheaders = [('User-agent', 'Google Chrome')]
return browser, cookiejar
def __init__(self):
self.cj = mechanize.LWPCookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(self.cj))
mechanize.install_opener(opener)
self.br = mechanize.Browser()
self.br.set_cookiejar(self.cj)
self.sessionkey = 'None'
self.br.set_header(
'User-Agent',
value=
'Mozilla/5.0 (X11; Linux x86_64; rv:73.0) Gecko/20100101 Firefox/73.0'
)
# self.br.set_debug_http(True)
self.br.set_debug_redirects(True)
def fillform(self, form, choice,questionid,sessionid,charturl,user,password):
if choice != "Random":
for i in range(1, 5):
form[questionid + str(i)] = [choice]
else:
for i in range(1, 5):
form[questionid + str(i)] = [str(random.randint(1, 5))]
data = form.click().get_data()
charturl += sessionid + "&questionid=" + questionid + "&qtype=" + "LS"
opener = self.addAuthentication(charturl, user, password)
mechanize.install_opener(opener)
req = mechanize.Request(charturl, data)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6')
req.add_header('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8')
req.add_header('Accept-Encoding', 'gzip,deflate')
def setUp(self):
mechanize._testcase.TestCase.setUp(self)
self.test_uri = urljoin(self.uri, "test_fixtures")
self.server = self.get_cached_fixture("server")
if self.no_proxies:
old_opener_m = mechanize._opener._opener
mechanize.install_opener(
mechanize.build_opener(mechanize.ProxyHandler(proxies={})))
install_opener(build_opener(ProxyHandler(proxies={})))
def revert_install():
mechanize.install_opener(old_opener_m)
install_opener(None)
self.add_teardown(revert_install)
def setUp(self):
mechanize._testcase.TestCase.setUp(self)
self.test_uri = urljoin(self.uri, "test_fixtures")
self.server = self.get_cached_fixture("server")
if self.no_proxies:
old_opener_m = mechanize._opener._opener
old_opener_u = urllib2._opener
mechanize.install_opener(mechanize.build_opener(
mechanize.ProxyHandler(proxies={})))
urllib2.install_opener(urllib2.build_opener(
urllib2.ProxyHandler(proxies={})))
def revert_install():
mechanize.install_opener(old_opener_m)
urllib2.install_opener(old_opener_u)
self.add_teardown(revert_install)
def __init__(self, username, password):
mechanize.Browser.__init__(self)
cj = mechanize.LWPCookieJar()
self.set_cookiejar(cj)
self.set_handle_equiv(True)
self.set_handle_redirect(True)
self.set_handle_referer(True)
self.set_handle_robots(False)
self.addheaders = [('User-agent', 'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1')]
self.open(self.base_url)
self.username = username
self.password = password
self.login()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cj))
mechanize.install_opener(opener)
def get_trash_zone(address, zip):
#Make cookie jar. See wwwsearch.sourceforge.dat/mechanize/hints.html
cj = mechanize.LWPCookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cj))
mechanize.install_opener(opener)
#Save cookies
cj.save(
"/usr/local/django/recyclocity/recyclocity_static/cookies/cookie_jar",
ignore_discard=True,
ignore_expires=True)
#Create a browser
browser = mechanize.Browser()
#Fill in form
browser.open('http://lmt-web.lowermerion.org/cgi-bin/refuse2.plx')
browser.form = list(browser.forms())[0]
browser.form['askrecycle'] = address
browser.form['postcode'] = zip
#Submit form
browser.submit()
#Extract content
content = browser.response().read()
#Use pattern match to extract fields
m = re.search('<b>(Monday|Tuesday|Wednesday|Thursday|Friday)</b>', content)
if m:
day, = m.groups()
#Convert day to number
day_number = schedule_helpers.get_day_number(day)
else:
#Failed
return
m = re.search('<b>Zone ([1-4])</b>', content)
if m:
zone, = m.groups()
else:
#Failed
return
#Match for both day and zone
return day_number, zone
def get_trash_zone(address, zip):
#Make cookie jar. See wwwsearch.sourceforge.dat/mechanize/hints.html
cj = mechanize.LWPCookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cj))
mechanize.install_opener(opener)
#Create a browser
browser = mechanize.Browser()
#User-Agent (this is cheating, ok?)
browser.addheaders = [(
'User-agent',
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1'
)]
#Save cookies
cj.save(
"/usr/local/django/recyclocity/recyclocity_static/cookies/cookie_jar",
ignore_discard=True,
ignore_expires=True)
#Fill in form
#browser.open('http://citymaps.phila.gov/portal/')
#browser.select_form(name="form1")
#browser.form['txtSearchAddress'] = address
#Fill in form
#browser.open('https://alpha.phila.gov/property/')
#browser.open('http://www.lowermerion.org/cgi-bin/recycle2.plx/')
browser.open(
'http://www.lowermerion.org/services/public-works-department/refuse-and-recycling/how-to-determine-your-recycling-collection-day'
)
#browser.form = list(browser.forms())[0]
#browser.form['askrecycle'] = address
#browser.form['postcode'] = zip
#Submit form
#browser.submit()
#Extract content
content = browser.response().read()
return content
def acm(query_str):
acm_url = u"http://dl.acm.org/"
cookieJar = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookieJar))
opener.addheaders = [("User-agent","Mozilla/5.0 (compatible)")]
mechanize.install_opener(opener)
fp = mechanize.urlopen(acm_url)
forms = mechanize.ParseResponse(fp, backwards_compat=False)
fp.close()
#doc = fetch(acm_url)
form = forms[0]
form['query'] = query_str
fp = mechanize.urlopen(form.click())
doc = fp.read()
with open("acm.html", 'wb') as fo:
fo.write(doc)
fp.close()
def _product_urls_and_types(cls, product_types):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [('User-agent', 'Mozilla/5.0 (MyProgram/0.1)'),
('From', '*****@*****.**')]
mechanize.install_opener(opener)
url_base = 'http://www.globalmac.cl/'
browser = mechanize.Browser()
url_extensions = [
['MacBook/', 'Notebook'],
['MacBook-Pro/', 'Notebook'],
['Monitores-LCD/', 'Monitor'],
['Cinema-Display/', 'Monitor'],
['Disco-Duro-SATA-2.5/', 'StorageDrive'],
['Discos-Duros-SATA/', 'StorageDrive'],
]
if 'Ram' in product_types:
memory_catalog_url = url_base + 'Memorias/'
base_data = browser.open(memory_catalog_url).get_data()
soup = BeautifulSoup(base_data)
subcats = soup.findAll('span', 'subcategories')
for subcat in subcats:
link = subcat.find('a')['href'].replace(url_base, '')
url_extensions.append([link, 'Ram'])
product_links = []
for url_extension, ptype in url_extensions:
if ptype not in product_types:
continue
base_data = browser.open(url_base + url_extension).get_data()
soup = BeautifulSoup(base_data)
titles = soup.findAll('a', 'product-title')
for title in titles:
product_links.append([title['href'], ptype])
return product_links
def __init__(self, username, password):
mechanize.Browser.__init__(self)
cj = mechanize.LWPCookieJar()
self.set_cookiejar(cj)
self.set_handle_equiv(True)
self.set_handle_redirect(True)
self.set_handle_referer(True)
self.set_handle_robots(False)
self.addheaders = [(
'User-agent',
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1'
)]
self.open(self.base_url)
self.username = username
self.password = password
self.login()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cj))
mechanize.install_opener(opener)
def go():
'''
Main procedure of the scraper. Creates a browser, load the list of tasks and execute them
'''
try:
# Prepare the browser
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
mechanize.install_opener(opener)
br = mechanize.Browser()
br.set_handle_robots(False)
br.set_handle_refresh(False)
br.set_handle_referer(False)
br.open("http://www.infogreffe.fr/infogreffe/process.do")
# Get the list of tasks
tasks = load_task_queue()
if len(tasks) == 0:
# If there is no task to execute, init/reset the table
init_task_queue()
tasks = load_task_queue()
for task in tasks:
try:
# Execute the task
results = get_companies(br, task['name'], task['dept'])
# If we hit the soft limit, add more refined searches to the queue
if results == 100:
print "Limit reached for %s in %s, adding new tasks" % (
task['name'], task['dept'])
expand_task_queue(task['name'], task['dept'])
# Mark the task as done
mark_task_done(task['name'], task['dept'], results)
except Exception as detail:
# We may get an exception for using too much CPU time.
print "Exception raised", detail
except Exception as detail:
# If we can't open the browser, just skip running the scraper
print "Failed starting browser ", detail
def fillform(self, form, choice, questionid, sessionid, charturl, user,
password):
if choice != "Random":
for i in range(1, 5):
form[questionid + str(i)] = [choice]
else:
for i in range(1, 5):
form[questionid + str(i)] = [str(random.randint(1, 5))]
data = form.click().get_data()
charturl += sessionid + "&questionid=" + questionid + "&qtype=" + "LS"
opener = self.addAuthentication(charturl, user, password)
mechanize.install_opener(opener)
req = mechanize.Request(charturl, data)
req.add_header(
'User-Agent',
'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'
)
req.add_header(
'Accept',
'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8')
req.add_header('Accept-Encoding', 'gzip,deflate')
def __init__(self, login=login.facebook):
super(KaggLoader, self).__init__()
self.login = login
self.set_handle_equiv(True)
self.set_handle_robots(False)
if not os.path.exists(self.BASE_DIR):
os.makedirs(self.BASE_DIR)
if not os.path.exists(self.COOKIE_PATH):
with open(self.COOKIE_PATH, 'w') as f:
f.write('#LWP-Cookies-2.0')
self.cj = mechanize.LWPCookieJar()
self.cj.load(self.COOKIE_PATH, ignore_discard=False, ignore_expires=False)
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(self.cj))
mechanize.install_opener(opener)
self.set_cookiejar(self.cj)
def pay_me_now(username, password):
if DEBUG:
import sys, logging
logger = logging.getLogger("mechanize")
logger.addHandler(logging.StreamHandler(sys.stdout))
logger.setLevel(logging.DEBUG)
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [("User-agent", "Mozilla/5.0 (compatible; BTCGPayOut/0.1)")]
mechanize.install_opener(opener)
br = mechanize.Browser()
if DEBUG:
br.set_debug_http(True)
br.set_debug_responses(True)
br.set_debug_redirects(True)
br.set_handle_robots(False)
# login
try:
br.open(URL_LOGIN)
br.select_form(predicate=select_login_form)
br['username'] = username
br['password'] = password
br.submit()
br.select_form(predicate=select_pay_me_now_form)
except:
print "Failed to login"
return
# logged in
try:
br.select_form(predicate=select_pay_me_now_form)
except:
print "Failed to find withdraw form"
return
br.submit()
def go():
'''
Main procedure of the scraper. Creates a browser, load the list of tasks and execute them
'''
try:
# Prepare the browser
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
mechanize.install_opener(opener)
br = mechanize.Browser()
br.set_handle_robots(False)
br.set_handle_refresh(False)
br.set_handle_referer(False)
br.open("http://www.infogreffe.fr/infogreffe/process.do")
# Get the list of tasks
tasks = load_task_queue()
if len(tasks) == 0:
# If there is no task to execute, init/reset the table
init_task_queue()
tasks = load_task_queue()
for task in tasks:
try:
# Execute the task
results = get_companies(br, task['name'], task['dept'])
# If we hit the soft limit, add more refined searches to the queue
if results == 100:
print "Limit reached for %s in %s, adding new tasks" % (task['name'], task['dept'])
expand_task_queue(task['name'], task['dept'])
# Mark the task as done
mark_task_done(task['name'], task['dept'], results)
except Exception as detail:
# We may get an exception for using too much CPU time.
print "Exception raised", detail
except Exception as detail:
# If we can't open the browser, just skip running the scraper
print "Failed starting browser ", detail
def logIn(self):
"""
Logs in to private archives using the supplied email and password.
Stores the cookie so we can continue to get subsequent pages.
"""
cookieJar = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookieJar))
opener.addheaders = [("User-agent","Mozilla/5.0 (compatible)")]
mechanize.install_opener(opener)
self.message('Logging in to '+self.list_url)
fp = mechanize.urlopen(self.list_url)
forms = ClientForm.ParseResponse(fp, backwards_compat=False)
fp.close()
form = forms[0]
form['username'] = self.username
form['password'] = self.password
fp = mechanize.urlopen(form.click())
fp.close()
def logIn(self):
"""
Logs in to private archives using the supplied email and password.
Stores the cookie so we can continue to get subsequent pages.
"""
cookieJar = mechanize.CookieJar()
opener = mechanize.build_opener(
mechanize.HTTPCookieProcessor(cookieJar))
opener.addheaders = [("User-agent", "Mozilla/5.0 (compatible)")]
mechanize.install_opener(opener)
self.message('Logging in to ' + self.list_url)
fp = mechanize.urlopen(self.list_url)
forms = ClientForm.ParseResponse(fp, backwards_compat=False)
fp.close()
form = forms[0]
form['username'] = self.username
form['password'] = self.password
fp = mechanize.urlopen(form.click())
fp.close()
def run(self):
self.tsession = Session()
try:
while True:
twitter_user_id = self.queue.get()
twitter_user = self.tsession.query(TwitterUser).filter(TwitterUser.id == twitter_user_id).first()
# Mechanize setup
cookies = cookielib.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [("User-agent",
"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6; en-us) AppleWebKit/533.4 (KHTML, like Gecko) Version/4.1 Safari/533.4")
, ]
mechanize.install_opener(opener)
# Load the twitter page
page = None
try:
tries = 5
while (tries > 0):
try:
page = mechanize.urlopen("https://mobile.twitter.com/" + twitter_user.twitter_screen_name)
except mechanize.HTTPError, e:
if e.code != 404:
tries = tries - 1
pass
else:
raise
except Exception, e:
raise
if tries == 0:
print "Error 403 para %s" % twitter_user.twitter_screen_name
sys.stdout.write("Error 403 para " + twitter_user.twitter_screen_name + "\n")
sys.stdout.flush()
self.queue.task_done()
continue
def getformpage(self, user, password, choice):
projectgroupurl = "http://leo.rp.edu.sg//workspace/studentModule.asp?site="
qnnurl = "http://leo3.rp.edu.sg//projectweb/group_evaluation.asp?"
quizurl = "http://leo3.rp.edu.sg//projectweb/qnn_take.asp?"
sessionurl = "http://leo3.rp.edu.sg//projectweb/qnn_preset.asp?"
charturl = "http://leo3.rp.edu.sg//projectweb/response_chart.asp?"
saveurl = "http://leo3.rp.edu.sg//projectweb/qnn_save_responses.asp"
urllist = []
for i in range(1, 4):
urllist.append(projectgroupurl + str(i))
# retrieve the result
currentModule = "projectid"
currentProblem = "groupid"
try:
for url in urllist:
opener = self.addAuthentication(url, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(url)
page = urlopen(response).read()
if ("Wrong Password" in page or "Wrong ID" in page):
self.vNP.set("Sorry, USERNAME or PASSWORD wrong!")
elif ('''ToggleDisplay''' in page):
currentModule = self.getidlist("projectid", page)[-1]
currentProblem = self.getidlist("groupid", page)[-1]
if (currentModule != "projectid" and currentProblem != "groupid"):
getqnnurl = qnnurl + currentModule + "&" + currentProblem + "&lang=ISO-8859-1"
opener = self.addAuthentication(getqnnurl, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(getqnnurl)
getqnnpage = urlopen(response)
forms = ParseResponse(getqnnpage, backwards_compat=False)
form = forms[0]
qnnid = form["qnnid"]
evalid = form["evalid"]
opener = self.addAuthentication(getqnnurl, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(getqnnurl)
getqnnpageread = urlopen(response).read()
author_evaluatorlist = re.findall(r"'\d{5}', '.{38}'",
getqnnpageread)
#for i in range(len(author_evaluatorlist)):
authorid = author_evaluatorlist[0][1:6]
evaluatorid = author_evaluatorlist[0][10:-1]
getsessionurl = sessionurl + "&qnnid=" + qnnid + "&" + currentModule + "&" + currentProblem + "&evalid=" + evalid + "&evaltype=P" + "&authorid=" + authorid + "&evaluatorid=" + evaluatorid + "&lang=ISO-8859-1"
opener = self.addAuthentication(getsessionurl, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(getsessionurl)
getqnnpage = urlopen(response)
forms = ParseResponse(getqnnpage, backwards_compat=False)
form = forms[0]
form.set_all_readonly(False)
form["qnnid"] = qnnid
form["authorid"] = authorid
form["evaluatorid"] = evaluatorid
form["evaltype"] = "P"
form["lang"] = "ISO-8859-1"
form["newflag"] = "0"
form["evalid"] = evalid
form["groupid"] = currentProblem[8:]
form["projectid"] = currentModule[10:]
submit = form.click()
data = submit.get_data()
opener = self.addAuthentication(quizurl, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(quizurl, data)
sessionid = self.getidlist("sessionid",
urlopen(response).read())[0]
answerurl = re.search(
"(\<FRAME NAME=\"main\" SRC=\")(.+)(\"\>)",
urlopen(response).read()).group(2)
answerurl = "http://leo3.rp.edu.sg//projectweb/" + answerurl
opener = self.addAuthentication(answerurl, user, password)
mechanize.install_opener(opener)
rs = mechanize.Request(answerurl, data)
quiz = urlopen(rs)
quizpage = urlopen(rs).read()
questionid = re.search(r"\{.+\}num", quizpage).group()[0:-3]
forms = ParseResponse(quiz, backwards_compat=False)
form = forms[0]
self.fillform(form, choice, questionid, sessionid, charturl,
user, password)
form.set_all_readonly(False)
form["finish"] = "MANUAL"
print form
'''
data = form.click().get_data()
opener = self.addAuthentication(saveurl, user, password)
mechanize.install_opener(opener)
req = mechanize.Request(saveurl, data)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6')
req.add_header('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8')
req.add_header('Accept-Encoding', 'gzip,deflate')
print urlopen(req).read()
'''
else:
self.vNP.set("Sorry, TODAY NO MODULE!")
except mechanize.HTTPError, e:
self.vNP.set(
"Error:",
BaseHTTPServer.BaseHTTPRequestHandler.responses[e.code])
def revert_install():
mechanize.install_opener(old_opener_m)
install_opener(None)
import mechanize cookies = mechanize.CookieJar() cookie_opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies)) mechanize.install_opener(cookie_opener) url = "http://www.webscantest.com/crosstraining/aboutyou.php" res = mechanize.urlopen(url) content = res.read() print len(content), content[0:100]
def __init__(self, ip):
self.ip = ip
self.neighbours = {}
self.laser_ports = {}
self.new_adm = False
#print(self.ip, type(self.ip))
self.baseurl = 'http://%s:20080/' % (self.ip)
try:
br = mechanize.Browser() #Create mechanize browser object
#Added false headers
try:
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(
mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [(
"User-agent",
"Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"
)]
mechanize.install_opener(opener)
except Exception as e:
print(str(e))
try:
if 'TJ1400' in br.open(self.baseurl, timeout=5.0).read():
self.new_adm = True
br.form = list(br.forms())[0]
controls = list(br.form.controls)
controls[0].value = 'tejas'
controls[1].value = 'j72e#05t'
page = br.submit()
self.new_adm = True
time.sleep(5)
page = br.open(self.baseurl, timeout=5.0).read()
except Exception as e:
#print("{}-{}".format(str(e), self.ip))
br = mechanize.Browser()
br.add_password(
self.baseurl, username, passw
) #Get user id and password from command line arguements
page = br.open(self.baseurl,
timeout=5.0).read() #Check if NE is accessible
self.new_adm = False
if 'alarmBanner' in page:
print "Logged in to %s" % (self.baseurl)
loggedIn = self.get_laser_data(br) #Read laser data of STM ports
failTime = threading.Thread(target=self.get_fail_time, args=(br, ))
failTime.start()
#self.get_fail_time(br) #Read alarams (MS DCC Fail only)
addNeighbours = threading.Thread(target=self.add_neighbours,
args=(br, ))
addNeighbours.start()
#self.add_neighbours(br) #Add neighbours
if loggedIn:
self.backup(br) #Backup cross-connect info
failTime.join()
addNeighbours.join()
#print(self.neighbours)
if self.alarams_dict:
for stm in self.alarams_dict.keys():
if stm in self.neighbours.keys():
fail_node_times = [[
self.ip, self.neighbours[stm][0],
self.alarams_dict[stm]
]]
fail_times.extend(fail_node_times)
except Exception as e:
print("\nError reading {} \n-+--+- {} -+--+-".format(ip, str(e)))
br.close()
return (None)
except urllib2.URLError, e:
#print e.read()
raise
data = r.read()
#print data
self.assert_(data.find("Your browser supports cookies!") >= 0)
self.assert_(len(cj) == 1)
# test response.seek() (added by HTTPEquivProcessor)
r.seek(0)
samedata = r.read()
r.close()
self.assert_(samedata == data)
finally:
o.close()
install_opener(None)
def test_robots(self):
plain_opener = mechanize.build_opener(
mechanize.HTTPRobotRulesProcessor)
browser = mechanize.Browser()
for opener in plain_opener, browser:
r = opener.open(urljoin(self.uri, "robots"))
self.assertEqual(r.code, 200)
self.assertRaises(mechanize.RobotExclusionError, opener.open,
urljoin(self.uri, "norobots"))
def test_urlretrieve(self):
url = urljoin(self.uri, "/mechanize/")
test_filename = "python.html"
import mechanize cookies = mechanize.CookieJar() cookie_opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies)) mechanize.install_opener(cookie_opener) url = "http://www.webscantest.com/crosstraining/aboutyou.php" res = mechanize.urlopen(url) content = res.read()
def login(self,className):
"""
Automatically generate a cookie file for the coursera site.
"""
#TODO: use proxy here
hn,fn = tempfile.mkstemp()
cookies = cookielib.LWPCookieJar()
handlers = [
urllib2.HTTPHandler(),
urllib2.HTTPSHandler(),
urllib2.HTTPCookieProcessor(cookies)
]
opener = urllib2.build_opener(*handlers)
url = self.lecture_url_from_name(className)
req = urllib2.Request(url)
try:
res = opener.open(req)
except urllib2.HTTPError as e:
if e.code == 404:
raise Exception("Unknown class %s" % className)
# get the csrf token
csrfcookie = [c for c in cookies if c.name == "csrf_token"]
if not csrfcookie: raise Exception("Failed to find csrf cookie")
csrftoken = csrfcookie[0].value
opener.close()
# call the authenticator url:
cj = cookielib.MozillaCookieJar(fn)
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj),
urllib2.HTTPHandler(),
urllib2.HTTPSHandler())
opener.addheaders.append(('Cookie', 'csrftoken=%s' % csrftoken))
opener.addheaders.append(('Referer', 'https://www.coursera.org'))
opener.addheaders.append(('X-CSRFToken', csrftoken))
req = urllib2.Request(self.LOGIN_URL)
data = urllib.urlencode({'email_address': self.username,'password': self.password})
req.add_data(data)
try:
opener.open(req)
except urllib2.HTTPError as e:
if e.code == 401:
raise Exception("Invalid username or password")
# check if we managed to login
sessionid = [c.name for c in cj if c.name == "sessionid"]
if not sessionid:
raise Exception("Failed to authenticate as %s" % self.username)
# all should be ok now, mechanize can handle the rest if we give it the
# cookies
br = mechanize.Browser()
#br.set_debug_http(True)
#br.set_debug_responses(False)
#br.set_debug_redirects(True)
br.set_handle_robots(False)
br.set_cookiejar(cj)
if self.proxy:
br.set_proxies({"http":self.proxy})
self.browser = br
# also use this cookiejar for other mechanize operations (e.g., urlopen)
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cj))
mechanize.install_opener(opener)
def getNewToken(self):
import mechanize #@UnresolvedImport
br = mechanize.Browser()
__addon__ = xbmcaddon.Addon(id='script.facebook.media')
cookiesPath = os.path.join(xbmc.translatePath(__addon__.getAddonInfo('profile')),'cache','cookies')
LOG('Cookies will be saved to: ' + cookiesPath)
cookies = mechanize.LWPCookieJar(cookiesPath)
if os.path.exists(cookiesPath): cookies.load()
self.cookieJar = cookies
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
mechanize.install_opener(opener)
br.set_cookiejar(self.cookieJar)
br._ua_handlers["_cookies"].cookiejar.clear()
br.set_handle_robots(False)
agent = 'XBMC/{0} Facebook-Media/{1}'.format(xbmc.getInfoLabel('System.BuildVersion'),self.version)
LOG('Setting User Agent: {0}'.format(agent))
br.addheaders = [('User-agent',agent)]
scope = ''
if self.scope: scope = '&scope=' + self.scope
url = 'https://www.facebook.com/dialog/oauth?client_id='+self.client_id+\
'&redirect_uri='+self.redirect+\
'&type=user_agent&display=popup'+scope
LOG(url)
try:
res = br.open(url)
html = res.read()
except:
LOG("ERROR: TOKEN PAGE INITIAL READ")
raise
script = False
try:
#check for login form
br.select_form(nr=0)
LOG("HTML")
except:
self.genericError()
script = True
LOG("SCRIPT")
if script:
#no form, maybe we're logged in and the token is in javascript on the page
url = res.geturl()
token = self.extractTokenFromURL(url)
if not token: token = self.parseTokenFromScript(html)
else:
try:
#fill out the form and submit
br['email'] = self.login_email
br['pass'] = self.login_pass
res = br.submit()
url = res.geturl()
LOG("FORM")
except:
LOG("FORM ERROR")
raise
script = False
token = self.extractTokenFromURL(url)
html = self.browserRead(res,'-noscript')
if not token:
#if 'class="checkpoint"' in html:
token = self.handleLoginNotificationCrap(br)
if not token: script = True
if script:
LOG("SCRIPT TOKEN")
#no token in the url, let's try to parse it from javascript on the page
try:
__addon__ = xbmcaddon.Addon(id='script.facebook.media')
htmlFile = os.path.join(xbmc.translatePath(__addon__.getAddonInfo('profile')),'cache','DEBUG_HTML.html')
open(htmlFile,'w').write(html)
LOG('html output written to: ' + htmlFile)
except:
pass
token = self.parseTokenFromScript(html)
token = urllib.unquote(token.decode('unicode-escape'))
if not self.tokenIsValid(token):
#if script: LOG("HTML:" + html)
return False
LOG("\n|--------------------\n|TOKEN: %s\n|--------------------" % token)
self.saveToken(token)
if self.cookieJar is not None:
self.cookieJar.save()
return token
def _product_urls_and_types(cls, product_types):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [('User-agent', 'Mozilla/5.0 (MyProgram/0.1)'),
('From', '*****@*****.**')]
mechanize.install_opener(opener)
url_buscar_productos = '/cl/'
product_links = []
url_base = 'http://www.dell.com'
# Start home
if 'Notebook' in product_types:
url_extensions = [
'p/laptops?cat=laptops',
]
for url_extension in url_extensions:
url_webpage = url_base + url_buscar_productos + url_extension
r = mechanize.urlopen(url_webpage)
soup = BeautifulSoup(r.read())
notebook_lines_container = soup.find('div',
'tabschegoryGroups')
notebook_lines = \
notebook_lines_container.findAll('div', recursive=False)
notebook_urls = []
for line in notebook_lines:
for container in line.findAll('div', 'prodImg'):
link = container.find('a')['href'].replace('pd', 'fs')
notebook_urls.append(url_base + link)
for url in notebook_urls:
for url in cls.retrieve_line_links(url):
product_links.append([url, 'Notebook'])
# Start business
url_extensions = [
'empresas/p/laptops',
]
for url_extension in url_extensions:
url_webpage = url_base + url_buscar_productos + url_extension
r = mechanize.urlopen(url_webpage)
soup = BeautifulSoup(r.read())
line_links = soup.find('div', 'content').findAll('a')
for link in line_links:
url = url_base + link['href']
for url in cls.retrieve_enteprise_links(url):
product_links.append([url, 'Notebook'])
# Start Monitor
if 'Monitor' in product_types:
url_extensions = [
'/content/products/compare.aspx/19_22widescreen'
'?c=cl&cs=cldhs1&l=es&s=dhs',
'/content/products/compare.aspx/23_30widescreen'
'?c=cl&cs=cldhs1&l=es&s=dhs',
'/cl/es/empresas/Monitores/19_15widescreen/cp.aspx'
'?refid=19_15widescreen&s=bsd&cs=clbsdt1',
'/cl/es/empresas/Monitores/22_20widescreen/cp.aspx'
'?refid=22_20widescreen&s=bsd&cs=clbsdt1',
'/cl/es/empresas/Monitores/30_24widescreen/cp.aspx'
'?refid=30_24widescreen&s=bsd&cs=clbsdt1',
'/cl/es/empresas/Monitores/20_19flatpanel/cp.aspx'
'?refid=20_19flatpanel&s=bsd&cs=clbsdt1',
]
for url_extension in url_extensions:
url_webpage = url_base + url_extension
r = mechanize.urlopen(url_webpage)
soup = BeautifulSoup(r.read())
links = soup.findAll('a', 'lnk')
for link in links:
if 'configure' in link['href']:
product_links.append([link['href'], 'Monitor'])
return product_links
def revert_install():
mechanize.install_opener(old_opener_m)
urllib2.install_opener(old_opener_u)
def getformpage(self, user, password, choice):
projectgroupurl = "http://leo.rp.edu.sg//workspace/studentModule.asp?site="
qnnurl = "http://leo3.rp.edu.sg//projectweb/group_evaluation.asp?"
quizurl = "http://leo3.rp.edu.sg//projectweb/qnn_take.asp?"
sessionurl = "http://leo3.rp.edu.sg//projectweb/qnn_preset.asp?"
charturl = "http://leo3.rp.edu.sg//projectweb/response_chart.asp?"
saveurl = "http://leo3.rp.edu.sg//projectweb/qnn_save_responses.asp"
urllist = []
for i in range (1, 4):
urllist.append(projectgroupurl + str(i))
# retrieve the result
currentModule = "projectid"
currentProblem = "groupid"
try:
for url in urllist:
opener = self.addAuthentication(url, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(url)
page = urlopen(response).read()
if ("Wrong Password" in page or "Wrong ID" in page):
self.vNP.set("Sorry, USERNAME or PASSWORD wrong!")
elif ('''ToggleDisplay''' in page):
currentModule = self.getidlist("projectid", page)[-1]
currentProblem = self.getidlist("groupid", page)[-1]
if (currentModule != "projectid" and currentProblem != "groupid"):
getqnnurl = qnnurl + currentModule + "&" + currentProblem + "&lang=ISO-8859-1"
opener = self.addAuthentication(getqnnurl, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(getqnnurl)
getqnnpage = urlopen(response)
forms = ParseResponse(getqnnpage, backwards_compat=False)
form = forms[0]
qnnid = form["qnnid"]
evalid = form["evalid"]
opener = self.addAuthentication(getqnnurl, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(getqnnurl)
getqnnpageread = urlopen(response).read()
author_evaluatorlist = re.findall(r"'\d{5}', '.{38}'", getqnnpageread)
#for i in range(len(author_evaluatorlist)):
authorid = author_evaluatorlist[0][1:6]
evaluatorid = author_evaluatorlist[0][10:-1]
getsessionurl = sessionurl + "&qnnid=" + qnnid + "&" + currentModule + "&" + currentProblem + "&evalid=" + evalid + "&evaltype=P" + "&authorid=" + authorid + "&evaluatorid=" + evaluatorid + "&lang=ISO-8859-1"
opener = self.addAuthentication(getsessionurl, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(getsessionurl)
getqnnpage = urlopen(response)
forms = ParseResponse(getqnnpage, backwards_compat=False)
form = forms[0]
form.set_all_readonly(False)
form["qnnid"] = qnnid
form["authorid"] = authorid
form["evaluatorid"] = evaluatorid
form["evaltype"] = "P"
form["lang"] = "ISO-8859-1"
form["newflag"] = "0"
form["evalid"] = evalid
form["groupid"] = currentProblem[8:]
form["projectid"] = currentModule[10:]
submit = form.click()
data = submit.get_data()
opener = self.addAuthentication(quizurl, user, password)
mechanize.install_opener(opener)
response = mechanize.Request(quizurl, data)
sessionid = self.getidlist("sessionid", urlopen(response).read())[0]
answerurl = re.search("(\<FRAME NAME=\"main\" SRC=\")(.+)(\"\>)", urlopen(response).read()).group(2)
answerurl = "http://leo3.rp.edu.sg//projectweb/" + answerurl
opener = self.addAuthentication(answerurl, user, password)
mechanize.install_opener(opener)
rs = mechanize.Request(answerurl, data)
quiz = urlopen(rs)
quizpage = urlopen(rs).read()
questionid = re.search(r"\{.+\}num", quizpage).group()[0:-3]
forms = ParseResponse(quiz, backwards_compat=False)
form = forms[0]
self.fillform(form, choice,questionid,sessionid,charturl,user,password)
form.set_all_readonly(False)
form["finish"] = "MANUAL"
print form
'''
data = form.click().get_data()
opener = self.addAuthentication(saveurl, user, password)
mechanize.install_opener(opener)
req = mechanize.Request(saveurl, data)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6')
req.add_header('Accept', 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8')
req.add_header('Accept-Encoding', 'gzip,deflate')
print urlopen(req).read()
'''
else:
self.vNP.set("Sorry, TODAY NO MODULE!")
except mechanize.HTTPError, e:
self.vNP.set("Error:",BaseHTTPServer.BaseHTTPRequestHandler.responses[e.code])
def login(self,className):
"""
Login into coursera and obtain the necessary session cookies.
"""
hn,fn = tempfile.mkstemp()
cookies = cookielib.LWPCookieJar()
handlers = [
urllib2.HTTPHandler(),
urllib2.HTTPSHandler(),
urllib2.HTTPCookieProcessor(cookies)
]
# prepend a proxy handler if defined
if(self.proxy):
proxy = urllib2.ProxyHandler({'http': self.proxy})
handlers = [proxy] + handlers
opener = urllib2.build_opener(*handlers)
url = self.lecture_url_from_name(className)
req = urllib2.Request(url)
try:
res = opener.open(req)
except urllib2.HTTPError as e:
if e.code == 404:
raise Exception("Unknown class %s" % className)
# get the csrf token
csrfcookie = [c for c in cookies if c.name == "csrf_token"]
if not csrfcookie: raise Exception("Failed to find csrf cookie")
csrftoken = csrfcookie[0].value
opener.close()
# call the authenticator url:
cj = cookielib.MozillaCookieJar(fn)
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cj),
urllib2.HTTPHandler(),
urllib2.HTTPSHandler())
opener.addheaders.append(('Cookie', 'csrftoken=%s' % csrftoken))
opener.addheaders.append(('Referer', 'https://accounts.coursera.org/signin'))
opener.addheaders.append(('X-CSRFToken', csrftoken))
req = urllib2.Request(self.LOGIN_URL)
data = urllib.urlencode({'email': self.username,'password': self.password})
req.add_data(data)
try:
opener.open(req)
except urllib2.HTTPError as e:
if e.code == 401:
raise Exception("Invalid username or password")
# check if we managed to login
sessionid = [c.name for c in cj if c.name == "CAUTH"]
if not sessionid:
raise Exception("Failed to authenticate as %s" % self.username)
# all should be ok now, mechanize can handle the rest if we give it the
# cookies
br = mechanize.Browser()
#br.set_debug_http(True)
#br.set_debug_responses(False)
#br.set_debug_redirects(True)
br.set_handle_robots(False)
br.set_cookiejar(cj)
if self.proxy:
br.set_proxies({"http":self.proxy})
self.browser = br
# also use this cookiejar for other mechanize operations (e.g., urlopen)
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cj))
mechanize.install_opener(opener)
def retrieve_product_links(self):
cookies = mechanize.CookieJar()
opener = mechanize.build_opener(mechanize.HTTPCookieProcessor(cookies))
opener.addheaders = [('User-agent', 'Mozilla/5.0 (MyProgram/0.1)'),
('From', '*****@*****.**')]
mechanize.install_opener(opener)
url_buscar_productos = '/cl/'
product_links = []
url_base = 'http://www.dell.com'
# Start home
url_extensions = [
'p/laptops?cat=laptops',
]
for url_extension in url_extensions:
url_webpage = url_base + url_buscar_productos + url_extension
r = mechanize.urlopen(url_webpage)
soup = BeautifulSoup(r.read())
notebook_lines_container = soup.find('div',
'tabschegoryGroups')
notebook_lines = notebook_lines_container.findAll('div',
recursive=False)
notebook_urls = []
for line in notebook_lines:
for container in line.findAll('div', 'prodImg'):
link = container.find('a')['href'].replace('pd', 'fs')
notebook_urls.append(url_base + link)
for url in notebook_urls:
for url in self.retrieve_line_links(url):
product_links.append([url, 'Notebook'])
# Start business
url_extensions = [
'empresas/p/laptops',
]
for url_extension in url_extensions:
url_webpage = url_base + url_buscar_productos + url_extension
r = mechanize.urlopen(url_webpage)
soup = BeautifulSoup(r.read())
product_containers = soup.findAll('div', 'carouselProduct')
for container in product_containers:
url = url_base + container.find('a')['href']
for url in self.retrieve_enteprise_links(url):
product_links.append([url, 'Notebook'])
# Start Monitor
url_extensions = [
'/content/products/compare.aspx/19_22widescreen'
'?c=cl&cs=cldhs1&l=es&s=dhs',
'/content/products/compare.aspx/23_30widescreen'
'?c=cl&cs=cldhs1&l=es&s=dhs',
'/cl/es/empresas/Monitores/19_15widescreen/cp.aspx'
'?refid=19_15widescreen&s=bsd&cs=clbsdt1',
'/cl/es/empresas/Monitores/22_20widescreen/cp.aspx'
'?refid=22_20widescreen&s=bsd&cs=clbsdt1',
'/cl/es/empresas/Monitores/30_24widescreen/cp.aspx'
'?refid=30_24widescreen&s=bsd&cs=clbsdt1',
'/cl/es/empresas/Monitores/20_19flatpanel/cp.aspx'
'?refid=20_19flatpanel&s=bsd&cs=clbsdt1',
]
for url_extension in url_extensions:
url_webpage = url_base + url_extension
r = mechanize.urlopen(url_webpage)
soup = BeautifulSoup(r.read())
links = soup.findAll('a', {'class': 'lnk'})
for link in links:
if 'configure' in link['href']:
product_links.append([link['href'], 'Screen'])
return product_links
def revert_install():
mechanize.install_opener(old_opener_m)
urllib2.install_opener(old_opener_u)
