def __init__(self, username=None, password=None, firefox_cookies=None,
parser=None, history=NoHistory(), proxy=None, logger=None):
"""
Constructor of Browser.
@param username [str] username on website.
@param password [str] password on website. If it is None, Browser will
not try to login.
@param filefox_cookies [str] Path to cookies' sqlite file.
@param parser [IParser] parser to use on HTML files.
@param hisory [object] History manager. Default value is an object
which does not keep history.
@param proxy [str] proxy URL to use.
"""
mechanize.Browser.__init__(self, history=history)
self.logger = getLogger('browser', logger)
self.addheaders = [
['User-agent', self.USER_AGENT]
]
# Use a proxy
self.proxy = proxy
if proxy:
proto = 'http'
if proxy.find('://') >= 0:
proto, domain = proxy.split('://', 1)
else:
domain = proxy
self.set_proxies({proto: domain})
# Share cookies with firefox
if firefox_cookies and HAVE_COOKIES:
self._cookie = FirefoxCookieJar(self.DOMAIN, firefox_cookies)
self._cookie.load()
self.set_cookiejar(self._cookie)
else:
self._cookie = None
if parser is None:
parser = get_parser()()
elif isinstance(parser, (tuple,list)):
parser = get_parser(parser)()
self.parser = parser
self.page = None
self.last_update = 0.0
self.username = username
self.password = password
self.lock = RLock()
if self.password:
try:
self.home()
# Do not abort the build of browser when the website is down.
except BrowserUnavailable:
pass
def __init__(
self,
firefox_cookies=None,
parser=None,
history=NoHistory(),
proxy=None,
logger=None,
factory=None,
responses_dirname=None,
):
mechanize.Browser.__init__(self, history=history, factory=factory)
self.logger = getLogger("browser", logger)
self.addheaders = [["User-agent", self.USER_AGENT]]
# Use a proxy
self.proxy = proxy
if proxy:
proto = "http"
if "://" in proxy:
v = urlsplit(proxy)
proto = v.scheme
domain = v.netloc
else:
domain = proxy
self.set_proxies({proto: domain})
# Share cookies with firefox
if firefox_cookies and HAVE_COOKIES:
self._cookie = FirefoxCookieJar(self.DOMAIN, firefox_cookies)
self._cookie.load()
self.set_cookiejar(self._cookie)
else:
self._cookie = None
if parser is None:
parser = get_parser()()
elif isinstance(parser, (tuple, list, str, unicode)):
parser = get_parser(parser)()
self.parser = parser
self.lock = RLock()
if self.DEBUG_HTTP:
# display messages from httplib
self.set_debug_http(True)
if self.DEBUG_MECHANIZE:
# Enable log messages from mechanize.Browser
self.set_debug_redirects(True)
self.responses_dirname = responses_dirname
def __init__(self,
firefox_cookies=None,
parser=None,
history=NoHistory(),
proxy=None,
logger=None,
factory=None,
responses_dirname=None):
mechanize.Browser.__init__(self, history=history, factory=factory)
self.logger = getLogger('browser', logger)
self.addheaders = [['User-agent', self.USER_AGENT]]
# Use a proxy
self.proxy = proxy
if proxy:
proto = 'http'
if '://' in proxy:
v = urlsplit(proxy)
proto = v.scheme
domain = v.netloc
else:
domain = proxy
self.set_proxies({proto: domain})
# Share cookies with firefox
if firefox_cookies and HAVE_COOKIES:
self._cookie = FirefoxCookieJar(self.DOMAIN, firefox_cookies)
self._cookie.load()
self.set_cookiejar(self._cookie)
else:
self._cookie = None
if parser is None:
parser = get_parser()()
elif isinstance(parser, (tuple, list, basestring)):
parser = get_parser(parser)()
self.parser = parser
self.lock = RLock()
if self.DEBUG_HTTP:
# display messages from httplib
self.set_debug_http(True)
if self.DEBUG_MECHANIZE:
# Enable log messages from mechanize.Browser
self.set_debug_redirects(True)
self.responses_dirname = responses_dirname
def get_current(self):
doc = self.browser.location('http://www.novaplanet.com/radionova/ontheair?origin=/')
html = doc['track']['markup']
parser = get_parser()()
doc = parser.parse(StringIO(html))
artist = u' '.join([txt.strip() for txt in doc.xpath('//div[@class="artist"]')[0].itertext()])
title = u' '.join([txt.strip() for txt in doc.xpath('//div[@class="title"]')[0].itertext()])
return unicode(artist).strip(), unicode(title).strip()
def get_current(self):
doc = self.browser.location('http://www.novaplanet.com/radionova/ontheair?origin=/')
html = doc['track']['markup']
parser = get_parser()()
doc = parser.parse(StringIO(html))
artist = u' '.join([txt.strip() for txt in doc.xpath('//div[@class="artist"]')[0].itertext()])
title = u' '.join([txt.strip() for txt in doc.xpath('//div[@class="title"]')[0].itertext()])
return unicode(artist).strip(), unicode(title).strip()
def __init__(self, firefox_cookies=None, parser=None, history=NoHistory(), proxy=None, logger=None, factory=None, responses_dirname=None):
mechanize.Browser.__init__(self, history=history, factory=factory)
self.logger = getLogger('browser', logger)
self.addheaders = [
['User-agent', self.USER_AGENT]
]
# Use a proxy
self.proxy = proxy
if proxy is not None:
self.set_proxies(proxy)
# Share cookies with firefox
if firefox_cookies and HAVE_COOKIES:
self._cookie = FirefoxCookieJar(self.DOMAIN, firefox_cookies)
self._cookie.load()
self.set_cookiejar(self._cookie)
else:
self._cookie = None
if parser is None:
parser = get_parser()()
elif isinstance(parser, (tuple,list,basestring)):
parser = get_parser(parser)()
self.parser = parser
self.lock = RLock()
if self.DEBUG_HTTP:
# display messages from httplib
self.set_debug_http(True)
if logging.root.level == logging.DEBUG:
# Enable log messages from mechanize.Browser
self.set_debug_redirects(True)
mech_logger = logging.getLogger("mechanize")
mech_logger.setLevel(logging.INFO)
self.responses_dirname = responses_dirname
self.responses_count = 0
def get_document(self, result, parser=None, encoding=None):
"""
Get a parsed document from a stream.
:param result: HTML page stream
:type result: stream
"""
if parser is None:
parser = self.parser
elif isinstance(parser, (basestring, list, tuple)):
parser = get_parser(parser)()
if encoding is None:
encoding = self.ENCODING
return parser.parse(result, encoding)
def get_document(self, result, parser=None, encoding=None):
"""
Get a parsed document from a stream.
:param result: HTML page stream
:type result: stream
"""
if parser is None:
parser = self.parser
elif isinstance(parser, (basestring, list, tuple)):
parser = get_parser(parser)()
if encoding is None:
encoding = self.ENCODING
return parser.parse(result, encoding)
