[Python] 從中央氣象局下載地震活動彙整列表

氣象局網站的 地震活動彙整 列表, 檢視網頁內容, 真正資料網頁連結為 https://scweb.cwb.gov.tw/Page.aspx/?ItemId=20&loc=tw&adv=1, 因為是ASP網頁, 所以需先取出ASP的傳遞參數, 資料表格之 class 為 datalist4, 使用 BeautifulSoup 即可取出表格內容

# -*- coding: utf-8 -*- """ Created on Sun Oct  15 11:53:25 2018 @author: ghosty @Program: cwbweb_list.py @Prupose: download quake data from CWB web source: https://www.cwb.gov.tw/V7/earthquake/rtd_eq.htm """ import requests from bs4 import BeautifulSoup #import dateutil    def downloadCWBweb(year,month):     url = 'https://scweb.cwb.gov.tw/Page.aspx/?ItemId=20&loc=tw&adv=1'                  agent = 'Mozilla/5.0 (Windows NT 6.3; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0'     headers = {'Content-type': 'application/x-www-form-urlencoded',            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',            'User-Agent': agent}     payload = {             '__VIEWSTATE':'',             '__VIEWSTATEGENERATOR':'',             '__VIEWSTATEENCRYPTED':'',             '__EVENTVALIDATION':'',             'ctl03_ddlYear':'',             'ctl03_ddlMonth':'',             'ctl03_btnSearch':''         }     response1 = requests.post(url)     if  response1.status_code != requests.codes.ok:         print("CWB requesr fail")         return         soup = BeautifulSoup(response1.text, "lxml")     payload['__VIEWSTATE']=soup.find('input',id='__VIEWSTATE')['value']         payload['__VIEWSTATEGENERATOR']=soup.find('input',id='__VIEWSTATEGENERATOR')['value']     payload['__VIEWSTATEENCRYPTE']=soup.find('input',id='__VIEWSTATEENCRYPTED')['value']     payload['__EVENTVALIDATION']=soup.find('input',id='__EVENTVALIDATION')['value']     payload['ctl03$ddlYear']="{:4d}".format(year)     payload['ctl03$ddlMonth']="{:0>2d}".format(month)     payload['ctl03$btnSearch']=''         response2 = requests.post(url,data=payload, headers=headers)     soup2 = BeautifulSoup(response2.text, "lxml")     table = soup2.find('table', attrs={'class':'datalist4'})     rows = table.find_all('tr')     quakeData  = []     for row in rows:         cols = row.find_all('td')         cols = [item.text.strip() for item in cols]         if (len(cols)>0): #skip empty row                    quakeData.append([item for item in cols if item]) # Get rid of empty values                 return quakeData quakeData = downloadCWBweb(2018,8) for data in quakeData:     print(data)