(url)
| 5 | |
| 6 | |
| 7 | def get_data(url): |
| 8 | html = rq.get(url).content.decode("gbk") |
| 9 | soup = BeautifulSoup(html, "html.parser") |
| 10 | tr_list = soup.find_all("tr") |
| 11 | dates, conditions, temperatures = [], [], [] |
| 12 | for data in tr_list[1:]: |
| 13 | sub_data = data.text.split() |
| 14 | dates.append(sub_data[0]) |
| 15 | conditions.append("".join(sub_data[1:3])) |
| 16 | temperatures.append("".join(sub_data[3:6])) |
| 17 | _data = pd.DataFrame() |
| 18 | _data["日期"] = dates |
| 19 | _data["天气状况"] = conditions |
| 20 | _data["气温"] = temperatures |
| 21 | return _data |
| 22 | |
| 23 | # 获取广州市2019年第一季度天气状况 |
| 24 | data_1_month = get_data("http://www.tianqihoubao.com/lishi/guangzhou/month/201901.html") |
no outgoing calls
no test coverage detected