Python Browser.geturl方法代码示例

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
    def _process(self):
        """Start the work."""
        movie = '+'.join(self.title.split())
        br = Browser()
        url = "%s/find?s=tt&q=%s" % (self.BASE_URL, movie)
        br.open(url)

        if re.search(r'/title/tt.*', br.geturl()):
            self.url = "%s://%s%s" % urlparse.urlparse(br.geturl())[:3]
            soup = BeautifulSoup( MyOpener().open(url).read() )
        else:
            link = br.find_link(url_regex = re.compile(r'/title/tt.*'))
            res = br.follow_link(link)
            self.url = urlparse.urljoin(self.BASE_URL, link.url)
            soup = BeautifulSoup(res.read())

        try:
            self.title = soup.find('h1').contents[0].strip()
            for span in soup.findAll('span'):
                if span.has_key('itemprop') and span['itemprop'] == 'ratingValue':
                    self.rating = span.contents[0]
                    break
            self.found = True
        except:
            pass

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
    def _process(self):
        """Start the work."""
        movie = "+".join(self.title.split())
        br = Browser()
        url = "%s/find?s=tt&q=%s" % (self.BASE_URL, movie)
        br.open(url)

        if re.search(r"/title/tt.*", br.geturl()):
            self.url = "%s://%s%s" % urlparse.urlparse(br.geturl())[:3]
            soup = BeautifulSoup(MyOpener().open(url).read(), "html.parser")
        else:
            link = br.find_link(url_regex=re.compile(r"/title/tt.*"))
            res = br.follow_link(link)
            self.url = urlparse.urljoin(self.BASE_URL, link.url)
            soup = BeautifulSoup(res.read(), "html.parser")

        try:
            self.title = soup.find("h1").contents[0].strip()
            for span in soup.findAll("span"):
                if span.has_attr("itemprop") and span["itemprop"] == "ratingValue":
                    self.rating = span.contents[0]
                    break
            self.found = True
        except:
            pass

        self.genre = []
        infobar = soup.find("div", {"class": "infobar"})
        r = infobar.find("", {"title": True})["title"]
        self.genrelist = infobar.findAll("a", {"href": True})

        for i in range(len(self.genrelist) - 1):
            self.genrelist[i] = self.genrelist[i].encode("ascii")
            self.genre.append(self.genrelist[i][16 : self.genrelist[i].index("?")])
        self.mainGenre = self.genre[0]

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
def check(acs):
    for a in acs:
        try:
            a = a.rsplit()[0]
        except:
            pass
        try:
            if a:
                a = a.split(':')
                user = a[0]
                passw = a[1]
                br = Browser()
                br.set_handle_gzip(True)
                br.set_handle_robots(False)
                br.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')]
                br.open('http://m.facebook.com/login.php')
                br.select_form(nr=0)
                br.form['email'] = user
                br.form['pass'] = passw
                br.submit()
                if 'm.facebook.com/login.php' in br.geturl() or 'checkpoint' in br.geturl() or 'to confirm your account with Facebook.' in br.response().read():
                            print "Could not login with " + str(a)

                else:
                    print "Logged in with " + user
                    opn = open(newfile, 'a')
                    opn.write(user + ":" + passw + '\n')
                    opn.close()

        except:
            print "Could not login with " + str(a)

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
def login_and_authorize(authorize_url, config):
    print "AUTHORIZING", authorize_url

    br = Browser()
    br.set_debug_redirects(True)
    br.open(authorize_url)
    print "FIRST PAGE", br.title(), br.geturl()

    br.select_form(nr=1)
    br['login_email'] = config['testing_user']
    br['login_password'] = config['testing_password']

    resp = br.submit()
    print "RESULT PAGE TITLE", br.title()
    print "RESULT URL", resp.geturl()

    assert br.viewing_html(), "Looks like it busted."

    try:
        br.select_form(nr=1)
        br.submit()
        br.viewing_html(), "Looks like it busted."
        assert "API Request Authorized" in br.title(), "Title Is Wrong (bad email/password?): %r at %r" % (br.title(), br.geturl())
    except FormNotFoundError:
        print "Looks like we're blessed."

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
class BachBrowser(object):
    def __init__(self):
        self._b = Browser()

    def login(self, user, pin):
        # submit login form
        login_data = urlencode({'yzbks': user, 'jklwd': pin})
        self._b.open(servlet_url('SSOLogin'), login_data)

        # open the content frame
        self._b.follow_link(name='content')

        # ack the "please don't forget to logout" form (if present)
        try:
            self._b.select_form('Main')
            self._b.submit()
        except FormNotFoundError:
            pass

        # store current session id
        self._b.select_form('Main')
        self._session_id = self._b['sessionid']

        # store the url of the "overview" page
        self._root_url = self._b.geturl()

    def logout(self):
        try:
            self._b.open(servlet_url('Logout'))
        except HTTPError, e:
            if e.code != 503:
                raise e

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
def getRatings(url):

	# url = 'http://us.imdb.com/M/title-exact?Moighty%20Aphrodite%20(1995)'
	try:
		br = Browser()
		br.set_handle_robots(False)
		br.open(url)

		if re.search(r'/title/tt.*', br.geturl()):
			soup = BeautifulSoup(MyOpener().open(url).read())
		else:
			link = br.find_link(url_regex = re.compile(r'/title/tt.*'))
			res = br.follow_link(link)
			soup = BeautifulSoup(res.read())
		
		# movie_title = soup.find('title').contents[0]
		des = (soup.find('meta',{'name':'description'})['content']).encode('utf-8')
		rate = soup.find('span',itemprop='ratingValue')
		# print movie_title
		# print des
	except:
		print 'Error no rating'
		rating = str(0)
		des = ""
	else:
		if rate:
			rating = str(rate.contents[0])
		else:
			rating = str(0)
			print 'No rate'
	
	return rating, des

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
    def get_browser(self):
        """
        Each FAUrl object stores it's own browser instance. On the first call
         it is created and if the username and password is set it will
         authenticate you.

        :return: mechanize.Browser instance.
        :raise: FAiler.FAError if FA is down. Time to F5!
        :raise: FAiler.FAAuth Your username and password failed
        """
        if self._br is None:
            br = Browser()
            br.set_handle_robots(False)
            br.set_handle_redirect(True)
            br.set_handle_referer(True)
            br.set_handle_equiv(True)
            br.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')]
            if self._username is not None and self._password is not None:
                loginPage = 'https://www.furaffinity.net/login'
                try:
                    br.open(loginPage)
                except urllib2.HTTPError:
                    raise FAError("FA's down, F5 time.")
                br.form = br.global_form()
                br.form['name'] = self._username
                br.form['pass'] = self._password
                br.form.method = 'POST'
                br.submit()
                if br.geturl() == loginPage + '/?msg=1':
                    raise FAAuth('Username & Password Incorrect')
            self._br = br
        return self._br

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
def login_and_authorize(argv=None):
    if argv is None:
       argv = sys.argv
    
    authorize_url = argv[1]
    config = json.loads(argv[2])
    
    print "AUTHORIZING", authorize_url
    br = Browser()
    br.set_debug_redirects(True)
    br.open(authorize_url)
    
    print "FIRST PAGE", br.title(), br.geturl()
    br.select_form(nr=2)
    br["login_email"] = config[u"testing_user"]
    br["login_password"] = config[u"testing_password"]

    resp = br.submit()
    print "RESULT PAGE TITLE", br.title()
    print "RESULT URL", resp.geturl()

    assert br.viewing_html(), "Looks like it busted."

    try:
        br.select_form(nr=2)
        br.submit()
        assert br.viewing_html(), "Looks like it busted."
        assert "API Request Authorized" in br.title(), "Title Is Wrong (bad email/password?): %r at %r" % (br.title(), br.geturl())
    except FormNotFoundError:
        print "Looks like we're blessed."
    
    return "OK"

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
    def _process(self):
        movie = '+'.join(self.title.split())
        br = Browser()
        url = "%s/find?s=tt&q=%s" % (self.BASE_URL, movie)
        br.open(url)
 
        if re.search(r'/title/tt.*', br.geturl()):
            self.url = "%s://%s%s" % urlparse.urlparse(br.geturl())[:3]
            soup = BeautifulSoup( MyOpener().open(url).read() )
        else:
            link = br.find_link(url_regex = re.compile(r'/title/tt.*'))
            res = br.follow_link(link)
            self.url = urlparse.urljoin(self.BASE_URL, link.url)
            soup = BeautifulSoup(res.read())
 
        try:
            self.title = soup.find('h1').contents[0].strip()
            self.rating = soup.find('span',attrs='rating-rating').contents[0]
            self.found = True
        except:
            pass

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
def testWebDip():
    br = Browser()
    br.open("http://webdiplomacy.net/logon.php")
    br.select_form(nr=0)
    br['loginuser'] = "USERNAMEHERE"
    br['loginpass'] = "PASSWORDHERE"
    br.submit()
    br.open("http://webdiplomacy.net/index.php")
    resp = br.reload()
    html = resp.read()
    soup = BeautifulSoup("".join(html))
    notices = soup.find("div", {"class": "gamelistings-tabs"})
    if notices is None:
        return
    elif notices.find("img", {"src": "images/icons/alert.png"}):
        webbrowser.open(br.geturl())
        print "It's your turn in WebDiplomacy"
        print ""
    elif notices.find("img", {"src": "images/icons/mail.png"}):
        webbrowser.open(br.geturl())
        print "You have mail in WebDiplomacy"
        print ""

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
    def _process(self):
        """Start the work."""
        movie = '+'.join(self.title.split())
        br = Browser()
        url = "%s/find?s=tt&q=%s" % (self.BASE_URL, movie)
        br.open(url)

        if re.search(r'/title/tt.*', br.geturl()):
            self.url = "%s://%s%s" % urlparse.urlparse(br.geturl())[:3]
            soup = BeautifulSoup( MyOpener().open(url).read() )
        else:
            link = br.find_link(url_regex = re.compile(r'/title/tt.*'))
            res = br.follow_link(link)
            self.url = urlparse.urljoin(self.BASE_URL, link.url)
            soup = BeautifulSoup(res.read())

        try:
            self.title = soup.find('h1').contents[0].strip()
            for span in soup.findAll('span'):
                if span.has_key('itemprop') and span['itemprop'] == 'ratingValue':
                    self.rating = span.contents[0]
                    break
            self.found = True
        except:
            pass

# class ImdbRating

# if __name__ == "__main__":
#     if len(sys.argv) == 1:
#         print "Usage: %s 'Movie title'" % (sys.argv[0])
#     else:
#         imdb = ImdbRating(sys.argv[1])
#         if imdb.found:
#             print imdb.url
#             print imdb.title
#             print imdb.rating

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
class Api:
    appid = '5415093'
    token = None
    query_pattern = 'https://api.vk.com/method/%s?%s&access_token='

    ua = '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'
    br = None
    cl = None

    def __init__(self, login, password, scope, testmode=False):
        self.br = Browser()
        self.cl = cookielib.LWPCookieJar()
        self.br.set_cookiejar(self.cl)

        self.br.set_handle_equiv(True)
        self.br.set_handle_redirect(True)
        self.br.set_handle_referer(True)
        self.br.set_handle_robots(False)
        self.br.set_handle_refresh(_http.HTTPRefreshProcessor(), max_time=1)
        self.br.addheaders = [('User-agent', self.ua)]

        self.br.open('https://oauth.vk.com/authorize?client_id=' + self.appid +
                     '&scope=' + scope + '&redirect_uri=http://oauth.vk.com/blank.html' +
                     '&display=mobile&response_type=token')

        self.br.select_form(nr=0)
        self.br.form['email'] = login
        self.br.form['pass'] = password
        self.br.submit()

        if len(list(self.br.forms())) > 0:
            self.br.select_form(nr=0)
            self.br.submit()

        params = urlparse.urlparse(self.br.geturl()).fragment
        params = params.split('&')

        for val in params:
            tp = val.split('=')
            if tp[0] == 'access_token':
                self.token = tp[1]
                self.query_pattern += self.token
                if testmode:
                    self.query_pattern += '&test_mode=1'
                break

    def query(self, func, data):
        response = self.br.open(self.query_pattern % (func, data))
        return response.read()

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
def get_product_url(item_list):
	"""
	Return the url for each item in item_list from flipkart.
	"""

	url_list = []
	br = Browser() #get the browser instance
	br.set_handle_robots(False) #ignore robot.txt
	br.addheaders = [('User-agent', 'Firefox')] # setting browser agent
	br.open("http://www.flipkart.com/") # open url

	for item in item_list:
		br.select_form(nr=1) #select form using postion, as form name is nor available
		br.form['q'] = item # set item to be searched
		br.submit()
		url_list.append(br.geturl())

	return url_list

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
class Scraper(object):
    def __init__(self):
        self.b = Browser()
        self.b.set_handle_robots(False)

        self.appkey = None
        self.GetAppKey()

    def GetAppKey(self):
        self.b.open("http://www.vancouversun.com/parking/basic-search.html")
        html = self.b.response().read()
        soup = BeautifulSoup(html)
        for div in soup.findAll('div'):
            if div.has_key('id') and div['id'] == 'cxkg':
                self.appkey = div.findAll('a')[0]['href'].split('AppKey=')[1].split('&')[0]
                logging.info('Got app key=%s', self.appkey)
                break

    def ScrapeTickets(self, page):
        assert len(self.appkey) > 10
        url = ENDPOINT % (self.appkey, page)
        logging.debug('Opening url: %s', url)
        startTime = time.time()
        self.b.open(url)
        logging.info('Loaded page in %d seconds', time.time() - startTime)

        logging.info('Starting to scrape tickets from page %d', page)

        doc = HTML.fromstring(self.b.response().read(), self.b.geturl())

        tickets = []
        fields = ["date", "Time", "plate", "make", "street_num", "street_name", "offence", "record_id"]
        for tr in doc.xpath("//table[1]/tr[@class='cbResultSetEvenRow'] | //table[1]/tr[@class='cbResultSetOddRow']"):
            values = [td.text for td in tr.getchildren()[:7]]
            td_details=tr.getchildren()[7]
            # get the RecordID
            values.append(re.search(recordID_regexp, td_details.xpath("a/@href")[0]).group(1))

            ticket = Ticket(zip(fields, values))
            ticket.CleanUpRawTicket()
            tickets.append(ticket)
        logging.info('Finished scraping %d tickets from page %d', len(tickets), page)
        return tickets

# 需要导入模块: from mechanize import Browser [as 别名]
# 或者: from mechanize.Browser import geturl [as 别名]
def main():
    cj = cookielib.LWPCookieJar('cookie.txt')
    try:
        cj.load('cookie.txt')
    except IOError:
        print "Кукисы не найдены"
    root_url = 'http://188.134.114.45/store1/admin/'
    admin_url ='http://188.134.114.45/store1/admin/index.php?route=common/home&token='
    suppler_url = "http://188.134.114.45/store1/admin/index.php?route=catalog/suppler/update&token="
    orinon1_url = '&suppler_id=1'
    orinon2_url = '&suppler_id=2'
    username = 'admin'
    userpass = '1q2w'
    br = Browser()
    br.set_handle_robots(False)
    br.set_cookiejar(cj)
    br.addheaders = [('User-agent', 'Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.0.6')]
    home_page = br.open(root_url)

    print br.title()


    br.select_form(nr=0)
    br["username"] = username
    br["password"] = userpass
    br.submit()
    token = getToken(br.geturl())
    cj.save('cookie.txt')

    br.open(suppler_url + token + orinon1_url)
    br.select_form(nr = 1)
    control = br.form.find_control("command")
    control.set_value_by_label(("Удалить товары",))

    res = br.submit()


    br.open(suppler_url + token + orinon2_url)
    br.select_form(nr = 1)
    control = br.form.find_control("command")
    control.set_value_by_label(("Удалить товары",))

    res = br.submit()