一、功能介绍
基于python爬虫下载全国水雨情信息http://xxfb.mwr.cn/sq_djdh.html
二、网页分析
三、代码
import requests
import pandas as pd
import os
# 存储中英文对应的变量的中文名
word_dict = {"poiAddv": "行政区",
"poiBsnm": "流域",
"ql": "流量(立方米/秒)",
"rvnm": "河名",
"stcd": "站点代码",
"stnm": "站名",
"tm": "时间",
"webStlc": "站址",
"wrz": "警戒水位(米)",
"zl": "水位(米)",
"dateTime": "日期"}
# 爬取大江大河实时水情
url = 'http://xxfb.mwr.cn/hydroSearch/greatRiver'
return_data = requests.get(url, verify=False)
js = return_data.json()
river_info = dict(js)["result"]["data"]
river_table = pd.DataFrame(river_info[0], index=[0])
for i in range(1, len(river_info)):
river_table = pd.concat([river_table, pd.DataFrame(river_info[i], index=[0])])
for str_col_name in ["poiAddv", "poiBsnm", "rvnm", "stnm", "webStlc"]:
river_table[str_col_name] = river_table[str_col_name].apply(lambda s: s.strip())
river_table.columns = [word_dict.get(i) for i in river_table.columns]
river_table.index = range(len(river_table.index))
"""
功能
保存爬取后得到的数据集river_table为.csv文件
输入
out_path:表格文件的输出路径,默认为桌面
"""
out_path = os.path.join(os.path.expanduser("~"), 'Desktop') # 输出路径,默认为桌面
date_suffix = river_table["时间"].values[0].split(" ")[0]
out_csv = os.path.join(out_path, "全国大江大河_{0}.csv".format(date_suffix)) # 输出文件名
river_table.to_csv(out_csv, encoding='utf_8_sig')
# 打印待保存的数据
print(river_table)
a = input("press any key to quit")
四、运行结果
五、其他
- 配合windows的计划任务功能实现每日自动运行
- 配合smtplib和email库可以实现邮件通知功能,参考代码如下:
import smtplib
from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
from email.mime.application import MIMEApplication
message = MIMEMultipart()
# 输入:发件邮箱
sender = 'xxxxx@126.com'
# 输入:收件邮箱
receiver = 'xxxxx@163.com'
# 输入:邮件申请SMTP服务后的密码
password = 'xxxxxxxxxx'
message['From'] = sender
message['To'] = receiver
content = "今日水情数据:{0}".format(date_suffix)
textApart = MIMEText(content)
# 输入:要添加到邮件中的附件
files = [out_csv]
for i in range(len(files)):
attFile = MIMEApplication(open(files[i], 'rb').read())
attFile.add_header('Content-Disposition', 'attachment', filename=os.path.split(files[i])[1])
message.attach(attFile)
message.attach(textApart) # 邮件的文字部分
message['Subject'] = date_suffix # 邮件的标题
try:
server = smtplib.SMTP('smtp.126.com') # 发件邮箱提供的SMTP服务器地址,这里以126邮箱为例
server.login(sender, password)
server.sendmail(sender, receiver, message.as_string())
print('success')
server.quit()
except smtplib.SMTPException as e:
print('error:', e) # 打印错误信息