def __init__(self, starting_url=False, save=False, initial_seed=False):
Crawler.__init__(self)
#No database values, just these attributes
self.url = starting_url if starting_url else self.base_url + "/w/Category:Artist"
self.save = save
self.initial_seed = initial_seed
#self.url = self.tree.xpath("//div[@class='listPagination'][1]/a[contains(text(), 'next')]/@href")[0]
return
def __init__(self, url, save=False, initial_seed=False):
Crawler.__init__(self)
#Database values
self.row_id = False
self.name = ''
self.url = url
#Other variables
self.save = save #If not saving, print for debugging and testing purposes
self.initial_seed = initial_seed
return
def __init__(self, dj_id, dj_name, url, save=False, initial_seed=False):
Crawler.__init__(self)
#Database values
self.row_id = False
self.dj_id = dj_id
self.url = url
self.track_ids = list()
self.multi_dj = False
self.multi_version = True
self.page_mod_time = False
#Other attributes, including xpath components
self.dj_name = dj_name
self.searchable_dj_name = self.dj_name.split("(")[0].strip()
self.no_comments_selector = "not(contains(@class,'commenttextfield'))"
self.tree = self.get_tree(url)
self.track_texts = list()
self.save = save #If not saving, print for debugging and testing purposes
self.initial_seed = initial_seed
return
