Example #1
0
    def test_parse_without_metalines(self):
        self.link = 'https://www.ptt.cc/bbs/NBA/M.1432438578.A.4B0.html'
        self.article_id = 'M.1432438578.A.4B0'
        self.board = 'NBA'

        jsondata = json.loads(crawler.parse(self.link, self.article_id, self.board))
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
Example #2
0
    def test_parse_with_push_without_contents(self):
        self.link = 'https://www.ptt.cc/bbs/Gossiping/M.1433091897.A.1C5.html'
        self.article_id = 'M.1433091897.A.1C5'
        self.board = 'Gossiping'

        jsondata = json.loads(crawler.parse(self.link, self.article_id, self.board))
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
Example #3
0
    def test_parse_with_push_without_contents(self):
        self.link = 'https://www.ptt.cc/bbs/Gossiping/M.1433091897.A.1C5.html'
        self.article_id = 'M.1433091897.A.1C5'
        self.board = 'Gossiping'

        jsondata = json.loads(crawler.parse(self.link, self.article_id, self.board))
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
Example #4
0
    def test_parse_without_metalines(self):
        self.link = 'https://www.ptt.cc/bbs/NBA/M.1432438578.A.4B0.html'
        self.article_id = 'M.1432438578.A.4B0'
        self.board = 'NBA'

        jsondata = json.loads(crawler.parse(self.link, self.article_id, self.board))
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
Example #5
0
    def test_parse_with_structured_push_contents(self):
        self.link = 'https://www.ptt.cc/bbs/Gossiping/M.1119222660.A.94E.html'
        self.article_id = 'M.1119222660.A.94E'
        self.board = 'Gossiping'

        jsondata = crawler.parse(self.link, self.article_id, self.board)
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
Example #6
0
    def test_parse(self):
        self.link = 'https://www.ptt.cc/bbs/PublicServan/M.1409529482.A.9D3.html'
        self.article_id = 'M.1409529482.A.9D3'
        self.board = 'PublicServan'

        jsondata = json.loads(crawler.parse(self.link, self.article_id, self.board))
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
        self.assertEqual(jsondata['message_conut']['count'], 57)
Example #7
0
    def test_parse(self):
        self.link = 'https://www.ptt.cc/bbs/PublicServan/M.1409529482.A.9D3.html'
        self.article_id = 'M.1409529482.A.9D3'
        self.board = 'PublicServan'

        jsondata = json.loads(crawler.parse(self.link, self.article_id, self.board))
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
        self.assertEqual(jsondata['message_count']['count'], 57)
Example #8
0
    def test_parse_with_structured_push_contents(self):
        self.link = 'https://www.ptt.cc/bbs/Gossiping/M.1119222660.A.94E.html'
        self.article_id = 'M.1119222660.A.94E'
        self.board = 'Gossiping'

        jsondata = json.loads(crawler.parse(self.link, self.article_id, self.board))
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
        isCatched = False
        for msg in jsondata['messages']:
            if u'http://tinyurl.com/4arw47s' in msg['push_content']:
                isCatched = True
        self.assertTrue(isCatched)
Example #9
0
    def test_parse_with_structured_push_contents(self):
        self.link = 'https://www.ptt.cc/bbs/Gossiping/M.1119222660.A.94E.html'
        self.article_id = 'M.1119222660.A.94E'
        self.board = 'Gossiping'

        jsondata = json.loads(crawler.parse(self.link, self.article_id, self.board))
        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
        isCatched = False
        for msg in jsondata['messages']:
            if u'http://tinyurl.com/4arw47s' in msg['push_content']:
                isCatched = True
        self.assertTrue(isCatched)
Example #10
0
    def test_parse(self):
        self.link = 'https://www.ptt.cc/bbs/PublicServan/M.1409529482.A.9D3.html'
        self.article_id = 'M.1409529482.A.9D3'
        self.board = 'PublicServan'

        jsondata = crawler.parse(self.link, self.article_id, self.board)
        self.assertIn('article_title', jsondata)
        self.assertIn('content', jsondata)
        self.assertIn('date', jsondata)
        self.assertIn('url', jsondata)
        self.assertIn('ip', jsondata)
        self.assertIn('board', jsondata)

        self.assertEqual(jsondata['article_id'], self.article_id)
        self.assertEqual(jsondata['board'], self.board)
        self.assertEqual(jsondata['message_count']['count'], 57)