def __init__(self):
self.crawler = Crawler()
self.region_url = {
"hololive": "hololive",
"en": "english",
"id": "indonesia"
}
class WebService(FlaskView):
def __init__(self):
self.crawler = Crawler()
self.region_url = {
"hololive": "hololive",
"en": "english",
"id": "indonesia"
}
@route("/health", methods=["GET"])
def health_check(self):
return jsonify({"status": "OK"}), 200
@route("/schedules", methods=["GET"])
@route("<string:region_code>/schedules", methods=["GET"])
def get_schedules(self, region_code=None):
if region_code == None:
return jsonify(self.crawler.get_schedules()), 200
elif self.region_url[region_code] != None:
return jsonify(
self.crawler.get_schedules(self.region_url[region_code])), 200
@route("/schedules/today", methods=["GET"])
@route("<string:region_code>/schedules/today", methods=["GET"])
def get_today_schedules(self, region_code=None):
if region_code == None:
print("region code unspecified")
return jsonify(self.crawler.get_today_schedules()), 200
elif self.region_url[region_code] != None:
return jsonify(
self.crawler.get_today_schedules(
self.region_url[region_code])), 200
class TestCrawler:
def setup_class(self):
self.crawler = Crawler()
def teardown_method(self):
pass
def test_get_date_schedules(self, container_soup):
date_schedules = self.crawler.get_date_schedules(container_soup)
assert 3 == len(date_schedules)
assert "08/26" == date_schedules[0].date
assert "08/27" == date_schedules[1].date
assert "08/28" == date_schedules[2].date
assert "天音かなた" == date_schedules[0].schedules[0].member
assert "00:00" == date_schedules[0].schedules[0].time
assert "猫又おかゆ" == date_schedules[2].schedules[0].member
def test_get_date_tags(self, container_soup):
container_tags = self.crawler.get_date_tags(container_soup)
assert 0 == container_tags[0][0]
assert 4 == container_tags[1][0]
assert 16 == container_tags[2][0]
assert "08/26" == container_tags[0][1]
assert "08/27" == container_tags[1][1]
assert "08/28" == container_tags[2][1]
def test_generate_schedule(self, schedule_soup):
schedule = self.crawler.generate_schedule(schedule_soup)
assert schedule.member == "獅白ぼたん"
assert schedule.time == "01:59"
assert schedule.youtube_url == "https://www.youtube.com/watch?v=vgX_7SD8Qts"
#!/usr/bin/env python3
#coding:utf8
from service.crawler import Crawler
if __name__ == '__main__':
crawler = Crawler()
crawler.run()
# 全部の歴史データを取得
data = requests.get('https://lab.isaaclin.cn/nCoV/api/area?latest=0')
data = data.json()
print("一共有{0}条记录。", len(data['results']))
res = data['results']
df = pd.DataFrame(res)
for i in range(len(df)):
df.iloc[i, 16] = time_c(df["updateTime"][0])
for i in range(len(df)):
df.iloc[i, 16] = df.iloc[i, 16][5:10]
# 去重部分代码
tem = df[df['updateTime'] == '03-02']
tem = tem.drop_duplicates(['provinceShortName'], keep='last')
for i in date[1:41]:
tem1 = df[df['updateTime'] == i]
tem1 = tem1.drop_duplicates(['provinceName'], keep='last')
tem = tem.append(tem1)
tem = tem.reset_index(drop=True)
timeline_bar().render_notebook()
if __name__ == '__main__':
crawler = Crawler()
main()
# crawler.run()
def lambda_handler(event, context):
crawler = Crawler()
crawler.run()
return {'statusCode': 200, 'body': json.dumps('Crawled successfully')}
def setup_class(self):
self.crawler = Crawler()