# 8.1 空氣品質監測網

這個網站可以讓我們根據選擇的地區看到空氣品質數據, 不過基於安全上的考量, 其對POST請求有一些特殊的限制, 就是除了跟查詢有關的表單資料外, 還要另外送出其他值: **\_\_VIEWSTATE**, **\_\_EVENTVALIDATION**以及**\_\_VIEWSTATEGENERATOR**. 這些額外的值都可以透過GET請求空氣品質監測網得到的response中獲得.

```python
import requests
from bs4 import BeautifulSoup


EPA_TAQM_URL = 'http://taqm.epa.gov.tw/taqm/tw/HourlyData.aspx'


def generate_query_form_data(start_date, end_date):
    resp = requests.get(EPA_TAQM_URL)
    dom = BeautifulSoup(resp.text, 'html5lib')
    view_state = dom.find(id='__VIEWSTATE')['value']
    event_validation = dom.find(id='__EVENTVALIDATION')['value']
    viewstate_generator = dom.find(id='__VIEWSTATEGENERATOR')['value']
    # In all the ctlxx$[var_name], the xx will change dynamically,
    # need to check the value before craw the web.
    # TODO: Refactor it to collect the xx value dynamically.
    form_data = {
        '__VIEWSTATE': view_state,
        '__EVENTVALIDATION': event_validation,
        '__VIEWSTATEGENERATOR': viewstate_generator,
        'ctl09$lbSite': '56',
        'ctl09$lbParam': '4',
        'ctl09$txtDateS': start_date,
        'ctl09$txtDateE': end_date,
        'ctl09$btnQuery': '查詢即時值'
    }
    return form_data


def get_web_content(start_date, end_date):
    form_data = generate_query_form_data(start_date, end_date)
    if form_data:
        resp = requests.post(EPA_TAQM_URL, data=form_data)
        dom = BeautifulSoup(resp.text, 'html5lib')
        return dom
    else:
        return None


def main():
    start_date = '2017/05/20'
    end_date = '2017/05/22'
    dom = get_web_content(start_date, end_date)
    if dom:
        for table in dom.find_all('table', 'TABLE_G'):
            print([s for s in table.stripped_strings])


if __name__ == '__main__':
    main()
```

輸出結果:

```javascript
['日期', '00', '01', '02', '03', '04', '05', '06', '07', '08', '09', '10', '11', '12', '13', '14', '15', '16', '17', '18', '19', '20', '21', '22', '23', '05/20', '34', '32', '38', '43', '40', '41', '43', '53', '55', '59', '65', '51', '36', '15', '25', '28', '40', '43', '36', '33', '27', '35', '42', '47', '05/21', '51', '54', '57', '59', '60', '64', '71', '66', '68', '59', '54', '35', '35', '39', '62', '59', '53', '37', '36', '35', '31', '34', '32', '36', '05/22', '30', '39', '37', '42', '39', '35', '36', '38', '45', '41', '35', '30', '43', '43', '45', '28', '22', '24', '27', '33', '30', '30', '21', '17']

Process finished with exit code 0
```

原始碼[點我](https://github.com/yotsuba1022/web-crawler-practice/blob/master/ch8/tw_epa_air_qlt.py)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://clu.gitbook.io/python-web-crawler-note/81-kong-qi-pin-zhi-jian-ce-wang.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.