class DepartmentScraper(Scraper):
def __init__(self, department):
self.department = department
self.infosource = InfoSource()
url = self.infosource.department_index(department)
return( super(DepartmentScraper,self).__init__(url ))
"""
return the link to the institution-specific list of data categories
for this department.
"""
def institution_data_page(self):
link_text = self.soup.find(text=re.compile("Institution-Specific Classes of Records"))
if link_text:
link = link_text.findParent('a')
return(self.infosource.department_page(self.department,link['href']))
else:
return( None )
"""
return the link to the standard list of data categories for this
department.
"""
def standard_data_page(self):
link_text = self.soup.find(text=re.compile("Standard Classes of Records"))
if link_text:
link = link_text.findParent('a')
return( self.infosource.department_page(self.department,link['href']))
else:
print "All departments should have a standard classes of record. None found on %s." % (self.cache.path)
return( None )
def scrape(self):
print "scraping department " + self.department.name
to_scrape = { self.standard_data_page() : DepartmentStandardCategoryScraper,
self.institution_data_page() : DepartmentSpecificCategoryScraper
}
for page, scraper_class in to_scrape.items():
if page:
scraper = scraper_class(self.department,page)
scraper.scrape()
def __init__(self, department):
self.department = department
self.infosource = InfoSource()
url = self.infosource.department_index(department)
return( super(DepartmentScraper,self).__init__(url ))
