def test_dealstr(self):
url = [
"<a href=\"/405964.html class=\"hello\" ",
"<a href=\"/66482.html class=\"hello\"",
"<a href=\"/11158.html class=\"hello\""
]
self.assertEqual(crawler.dealstr(url), ["405964.", "66482.", "11158."])
def test_againdeal(self):
firstweb = requests.get('https://tw.news.yahoo.com/society/')
firstweb.encoding = 'utf-8'
book = firstweb.text
m = re.findall('<a href=\"/.*html\" class=\"title \"', book) #m is search all urs list
url_list = [crawler.dealstr(m)[0]]
base_url = 'https://tw.news.yahoo.com/'
with open('t.json', "wt", encoding = 'utf-8') as output:
class_list = crawler.againdeal(url_list, output, base_url)
with open('t.json', 'rt', encoding = 'utf-8') as result:
self.assertNotEqual(len(result.read()), 0)
os.remove('t.json')
def test_againdeal(self):
firstweb = requests.get('https://tw.news.yahoo.com/society/')
firstweb.encoding = 'utf-8'
book = firstweb.text
m = re.findall('<a href=\"/.*html\" class=\"title \"',
book) #m is search all urs list
url_list = [crawler.dealstr(m)[0]]
base_url = 'https://tw.news.yahoo.com/'
with open('t.json', "wt", encoding='utf-8') as output:
class_list = crawler.againdeal(url_list, output, base_url)
with open('t.json', 'rt', encoding='utf-8') as result:
self.assertNotEqual(len(result.read()), 0)
os.remove('t.json')
# use 'python -m unittest test.py' to test
#or use 'notetests test.py' to test in the cmd
def test_dealstr(self):
url = ["<a href=\"/405964.html class=\"hello\" ", "<a href=\"/66482.html class=\"hello\"", "<a href=\"/11158.html class=\"hello\""]
self.assertEqual(crawler.dealstr(url), ["405964.", "66482.", "11158."])