def test_crawler(self):
crawler(['-b', 'PublicServan', '-i', '1', '2'])
filename = 'PublicServan-1-2.json'
with codecs.open(filename, 'r', encoding='utf-8') as f:
data = json.load(f)
# M.1127808641.A.C03.html is empty, so decrease 1 from 40 articles
self.assertEqual(len(data['articles']), 39)
data = crawler.get(filename)
self.assertEqual(len(data['articles']), 39)
os.remove(filename)
def test_crawler(self):
crawler(['-b', 'PublicServan', '-i', '1', '2'])
filename = 'PublicServan-1-2.json'
with codecs.open(filename, 'r', encoding='utf-8') as f:
data = json.load(f)
# M.1127808641.A.C03.html is empty, so decrease 1 from 40 articles
self.assertEqual(len(data['articles']), 39)
data = crawler.get(filename)
self.assertEqual(len(data['articles']), 39)
os.remove(filename)
if __name__ == '__main__':
token = "ddddddddddddddddd"
board = "Beauty"
push_num = 10 #推文數門檻
last_page = crawler.getLastPage(board)
index_start = last_page - 1
index_end = last_page
filename = '{0}-{1}-{2}.json'.format(board, index_start, index_end)
crawler(['-b', board, '-i', str(index_start), str(index_end)])
# with codecs.open(filename, 'r', encoding='utf-8') as f:
# data = json.load(f)
# M.1127808641.A.C03.html is empty, so decrease 1 from 40 articles
#self.assertEqual(len(data['articles']), 39)
data = crawler.get(filename)
os.remove(filename)
articles = data['articles']
for a in articles:
title = a['article_title']
article_id = a['article_id']
url = a['url']
content = a['content']
push = a['message_count']['push']
if push >= push_num and article_id not in history_list:
print(push, title, url)
history_list.append(article_id)
imgs_url = parse_URL(content)
lineNotify(token, "{0} {1}".format(title, url))
for u in imgs_url:
lineNotifyPic(token, title, u)
