def __init__(self, name=None, **kwargs):
XMLFeedSpider.__init__(self, name=name, **kwargs)
whitelistFile = open('whitelist_urls_test.csv')
for line in whitelistFile:
feed_url = line.split(',')[1]
self.start_urls.append(feed_url)
self.visited_urls[feed_url] = {}
self.logger_file.write("Started")
def __init__(self, *arg, **argdict):
logging.info('---------------------%s--------------' % dir(self))
self.titleXpath = ''
self.descriptionXpath = ''
self.descriptionLenght = 0
self.linkXpath = ''
self.imgUrlXpath = ''
self.imageNum = 1
self.videoUrlXpath = ''
self.pubDateXpath = ''
self.guidXpath = ''
self.rule_id = ''
self.is_remove_namespaces = False
self.initConfig(argdict)
XMLFeedSpider.__init__(self, *arg)
self.currentNode = None
def __init__(self, *arg, **argdict):
logging.info('---------------------%s--------------' % dir(self))
self.titleXpath = ''
self.descriptionXpath = ''
self.descriptionLenght = 0
self.linkXpath = ''
self.imgUrlXpath = ''
self.imageNum = 1
self.videoUrlXpath = ''
self.pubDateXpath = ''
self.guidXpath = ''
self.rule_id = ''
self.is_remove_namespaces = False
self.initConfig(argdict)
XMLFeedSpider.__init__(self, *arg)
self.currentNode = None
def __init__(self,*arg,**argdict):
self.initConfig(*arg,**argdict)
XMLFeedSpider.__init__(*arg,**argdict)
def __new__(cls, *args, **kwargs):
if not hasattr(cls, "_instance"):
cls._instance = XMLFeedSpider.__new__(cls, *args, **kwargs)
cls.start_urls = get_vide_page_list(cls.index_url)
return cls._instance
def __init__(self, vin, *args, **kwargs):
logging.info("Spider " + self.name + " is calling")
XMLFeedSpider.__init__(self).__init__(*args, **kwargs)
self.vin = vin