def link_address_is_none():
config = Config(hostname='phila.legistar.com',
sponsor_links=False).defaults(DEFAULT_CONFIG)
scraper = LegistarScraper(config)
from BeautifulSoup import BeautifulSoup
link = BeautifulSoup('<html><a></a></html>').find('a')
address = scraper._get_link_address(link)
assert_is_none(address)
def link_address_is_none():
config = Config(hostname="phila.legistar.com", sponsor_links=False).defaults(DEFAULT_CONFIG)
scraper = LegistarScraper(config)
from BeautifulSoup import BeautifulSoup
link = BeautifulSoup("<html><a></a></html>").find("a")
address = scraper._get_link_address(link)
assert_is_none(address)
def link_address_is_none():
config = {"hostname": "phila.legistar.com", "fulltext": True}
scraper = LegistarScraper(config)
from BeautifulSoup import BeautifulSoup
link = BeautifulSoup("<html><a></a></html>").find("a")
address = scraper._get_link_address(link)
assert_is_none(address)
def link_address_is_onclick():
config = {"hostname": "phila.legistar.com", "fulltext": True}
scraper = LegistarScraper(config)
from BeautifulSoup import BeautifulSoup
link = BeautifulSoup("<html><a onclick=\"radopen('http://www.google.com');\"></a></html>").find("a")
address = scraper._get_link_address(link)
assert_equal(address, "http://www.google.com")
def link_address_is_href():
config = {"hostname": "phila.legistar.com", "fulltext": True}
scraper = LegistarScraper(config)
from BeautifulSoup import BeautifulSoup
link = BeautifulSoup('<html><a href="http://www.google.com"></a></html>').find("a")
address = scraper._get_link_address(link)
assert_equal(address, "http://www.google.com")
def link_address_is_onclick():
config = Config(hostname="phila.legistar.com", sponsor_links=False).defaults(DEFAULT_CONFIG)
scraper = LegistarScraper(config)
from BeautifulSoup import BeautifulSoup
link = BeautifulSoup("<html><a onclick=\"radopen('http://www.google.com');\"></a></html>").find("a")
address = scraper._get_link_address(link)
assert_equal(address, "http://www.google.com")
def link_address_is_href():
config = Config(hostname='phila.legistar.com',
sponsor_links=False).defaults(DEFAULT_CONFIG)
scraper = LegistarScraper(config)
from BeautifulSoup import BeautifulSoup
link = BeautifulSoup(
'<html><a href="http://www.google.com"></a></html>').find('a')
address = scraper._get_link_address(link)
assert_equal(address, 'http://www.google.com')