[Python知识库]Python爬虫-定时发送天气情况（附源码）

以前

定闹钟的意义是每天叫我起床

现在

我觉得

是该报达他的时候了

于是我

每天叫闹钟起床

众所周知

早上的时光很慢

眼睛一闭一睁

才过了五分钟

早上的时光很快

眼镜一闭一睁

就迟到五分钟

为了在有限的时间里做更多的事情

那就得把起床前必做的事情

列成清单

《情侣间必做的一百件事》

啊呸

《起床前必做的一百件事》

分析：

1、每天定时发送 当日的天气、热搜、以及其他你所关心的事情

2、发送格式为邮件发送

翠花，上酸菜：

1、抓取微博热搜信息

def GetWeiboRealtimeHotInfos(maxCount=10) :
    headUrl = "https://s.weibo.com/"
    hotUrl = "https://s.weibo.com/top/summary?cate=realtimehot"
    res = requests.get(hotUrl)
    res.raise_for_status()
    #print(res.text)
    res.encoding = res.apparent_encoding

    strInfo = "\n今日微博热搜：\n"
    pattern = '<a href=".*?" target=".*?">.*?</a>'
    re_result = re.findall(pattern, res.text)
    for i, result in enumerate(re_result) :
        pattern = '>(.*?)<'
        result_text = re.findall(pattern, result)
        if len(result_text) > 0 :
            strInfo = strInfo + result_text[0] + "\n"
        #print(result_text)

        pattern = '<a href="(.*?)"'
        result_url = re.findall(pattern, result)
        if len(result_url) > 0 :
            strInfo = strInfo + headUrl + result_url[0] + "\n"
            #print(headUrl + result_url[0])
        if i >= maxCount-1 :
            break
    return strInfo

注：此处只有代码，详细解释可以参考前一篇文章，内有详细信息以及代码含义解释：

《Python-爬虫教程（抓取微博热搜、附源码）》

可以关注微信公众号查看内容：

?

2、抓取当日天气信息。此处和抓取微博热搜不同，微博热搜抓取的数据格式使用正则表达式筛选，这里仅需要json化就可以

def GetWeatherInfo(cityName) :
    weatherJsonUrl = WEATHER_URL + cityName
    response = requests.get(weatherJsonUrl)  # 获取并下载页面，其内容会保存在respons.text里
    response.raise_for_status()  # 请求失败的话就会抛出异常

    # 将json文件格式导入成python的格式
    weatherData = json.loads(response.text)
    #print(weatherData)

    weather_dict = dict()
    weather_dict['type'] = weatherData['data']['forecast'][0]['type']
    weather_dict['high'] = weatherData['data']['forecast'][0]['high']
    weather_dict['low'] = weatherData['data']['forecast'][0]['low']
    weather_dict['fengxiang'] = weatherData['data']['forecast'][0]['fengxiang']
    weather_dict['ganmao'] = weatherData['data']['ganmao']

    logInfo = cityName + ": "
    for i, value in enumerate(weather_dict.values()) :
        logInfo += value
        if i < len(weather_dict.values())-1 :
            logInfo += ", "
        else :
            logInfo += "\n"
    #print(logInfo)
    return logInfo

3、像我这么传统的人，必须关注一下老黄历。

def GetHuangliInfo() :
    # 抓取黄历
    res = requests.get(HUANGLI_URL)
    res.raise_for_status()
    #print(res.text)
    res.encoding = res.apparent_encoding
    # 正则表达式筛选图片下级地址
    pattern = '<p>(.*?)</p>'
    re_result = re.findall(pattern, res.text)
    #print(re_result)

    strInfo = ""
    for i, result in enumerate(re_result) :
        if i == 0 :
            #print("\n老黄历：")
            strInfo = "\n老黄历：\n"
        result = result.replace('<span>', '')
        result = result.replace('</span>', '')
        result = result.replace('<strong>', '')
        result = result.replace('</strong>', '')
        result = result.replace('<span class="yj2y">', '')
        result = result.replace('<span class="sc2title">', '')
        #print("    >>>", result)
        strInfo += ("    >>>" + result + "\n")
        if i >= 9 :
            break
    return strInfo

4、定时发送。反正此脚本只做一件事，那就是每天给我发送邮件，所以定时操作可以简单点来，直接sleep到对应时间即可。

def GetSubSendMailTime(lastSendMailTime) :
    # 定时 7:30发送
    nowTime = time.time()
    if 0 == lastSendMailTime :
        localTime = time.localtime(nowTime)
        if localTime.tm_hour >= REMIND_TIME_HOUR :
            localTime = time.localtime(nowTime + (24-REMIND_TIME_HOUR+1)*3600)
        timeArray = "%d-%d-%d %d:%d:%d" % (localTime.tm_year, localTime.tm_mon, localTime.tm_mday, REMIND_TIME_HOUR, REMIND_TIME_MIN, 0)
        timeObj = time.strptime(timeArray, "%Y-%m-%d %H:%M:%S")
        timeStamp = int(time.mktime(timeObj))
        return int(timeStamp - nowTime)
    else :
        localTime = time.localtime(nowTime + 86400)
        timeArray = "%d-%d-%d %d:%d:%d" % (localTime.tm_year, localTime.tm_mon, localTime.tm_mday, REMIND_TIME_HOUR, REMIND_TIME_MIN, 0)
        timeObj = time.strptime(timeArray, "%Y-%m-%d %H:%M:%S")
        timeStamp = int(time.mktime(timeObj))
        return int(timeStamp - nowTime)

然后，执行脚本。因为此脚本需要在后台一直运行，所以直接放到永不关机的开发机上，注意，执行命令时需要使用 nohup，防止连接关闭，进程被干掉。

eg:?nohup python weather.py &

执行效果（源码在末尾！！！）：

源码：

# -*- encoding:utf8 -*-

import json
import requests
import re
import smtplib
from email.mime.text import MIMEText # 文本
from email.header import Header
import time
import datetime
import sys 
reload(sys)
sys.setdefaultencoding('utf-8')


WEATHER_URL    = "http://wthrcdn.etouch.cn/weather_mini?city="
HUANGLI_URL    = "https://www.huangli8.com"
MAIL_HOST      = "smtp.163.com"               # 指定SMTP服务器
MAIL_SENDER    = "zhanglu_1024@163.com"       # 发件人
MAIL_PASS      = "ZSKV"           # 授权码 并非密码，具体授权码开启方式百度，非常简单
MAIL_RECEIVERS = ['1044878451@qq.com']        # 收件人们
REMIND_TIME_HOUR = 7
REMIND_TIME_MIN  = 50

def GetWeatherInfo(cityName) :
    weatherJsonUrl = WEATHER_URL + cityName
    response = requests.get(weatherJsonUrl)  # 获取并下载页面，其内容会保存在respons.text里
    response.raise_for_status()  # 请求失败的话就会抛出异常

    # 将json文件格式导入成python的格式
    weatherData = json.loads(response.text)
    #print(weatherData)

    weather_dict = dict()
    weather_dict['type'] = weatherData['data']['forecast'][0]['type']
    weather_dict['high'] = weatherData['data']['forecast'][0]['high']
    weather_dict['low'] = weatherData['data']['forecast'][0]['low']
    weather_dict['fengxiang'] = weatherData['data']['forecast'][0]['fengxiang']
    weather_dict['ganmao'] = weatherData['data']['ganmao']

    logInfo = cityName + ": "
    for i, value in enumerate(weather_dict.values()) :
        logInfo += value
        if i < len(weather_dict.values())-1 :
            logInfo += ", "
        else :
            logInfo += "\n"
    #print(logInfo)
    return logInfo

def GetHuangliInfo() :
    # 抓取黄历
    res = requests.get(HUANGLI_URL)
    res.raise_for_status()
    #print(res.text)
    res.encoding = res.apparent_encoding
    # 正则表达式筛选图片下级地址
    pattern = '<p>(.*?)</p>'
    re_result = re.findall(pattern, res.text)
    #print(re_result)

    strInfo = ""
    for i, result in enumerate(re_result) :
        if i == 0 :
            #print("\n老黄历：")
            strInfo = "\n老黄历：\n"
        result = result.replace('<span>', '')
        result = result.replace('</span>', '')
        result = result.replace('<strong>', '')
        result = result.replace('</strong>', '')
        result = result.replace('<span class="yj2y">', '')
        result = result.replace('<span class="sc2title">', '')
        #print("    >>>", result)
        strInfo += ("    >>>" + result + "\n")
        if i >= 9 :
            break
    return strInfo

def SendMail(strInfo) :
    if len(MAIL_RECEIVERS) == 0 :
        return 

    message = MIMEText(strInfo, 'plain', 'utf-8') # 参数分别为文本，格式，编码
    message['From'] = MAIL_SENDER
    message['To'] = MAIL_RECEIVERS[0]
    
    subject = 'Python Mail ' + time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
    message['Subject'] = Header(subject, 'utf-8')
    
    try :
        smtpObj = smtplib.SMTP()
        smtpObj.connect(MAIL_HOST, 25)
        smtpObj.login(MAIL_SENDER, MAIL_PASS)
        smtpObj.sendmail(MAIL_SENDER, MAIL_RECEIVERS, message.as_string())
        print('send success')
    except smtplib.SMTPException :
        print('send error')

def GetWeiboRealtimeHotInfos(maxCount=10) :
    headUrl = "https://s.weibo.com/"
    hotUrl = "https://s.weibo.com/top/summary?cate=realtimehot"
    res = requests.get(hotUrl)
    res.raise_for_status()
    #print(res.text)
    res.encoding = res.apparent_encoding

    strInfo = "\n今日微博热搜：\n"
    pattern = '<a href=".*?" target=".*?">.*?</a>'
    re_result = re.findall(pattern, res.text)
    for i, result in enumerate(re_result) :
        pattern = '>(.*?)<'
        result_text = re.findall(pattern, result)
        if len(result_text) > 0 :
            strInfo = strInfo + result_text[0] + "\n"
        #print(result_text)

        pattern = '<a href="(.*?)"'
        result_url = re.findall(pattern, result)
        if len(result_url) > 0 :
            strInfo = strInfo + headUrl + result_url[0] + "\n"
            #print(headUrl + result_url[0])
        if i >= maxCount-1 :
            break
    return strInfo

def GetSubSendMailTime(lastSendMailTime) :
    # 定时 7:30发送
    nowTime = time.time()
    if 0 == lastSendMailTime :
        localTime = time.localtime(nowTime)
        if localTime.tm_hour >= REMIND_TIME_HOUR :
            localTime = time.localtime(nowTime + (24-REMIND_TIME_HOUR+1)*3600)
        timeArray = "%d-%d-%d %d:%d:%d" % (localTime.tm_year, localTime.tm_mon, localTime.tm_mday, REMIND_TIME_HOUR, REMIND_TIME_MIN, 0)
        timeObj = time.strptime(timeArray, "%Y-%m-%d %H:%M:%S")
        timeStamp = int(time.mktime(timeObj))
        return int(timeStamp - nowTime)
    else :
        localTime = time.localtime(nowTime + 86400)
        timeArray = "%d-%d-%d %d:%d:%d" % (localTime.tm_year, localTime.tm_mon, localTime.tm_mday, REMIND_TIME_HOUR, REMIND_TIME_MIN, 0)
        timeObj = time.strptime(timeArray, "%Y-%m-%d %H:%M:%S")
        timeStamp = int(time.mktime(timeObj))
        return int(timeStamp - nowTime)

def main() :
    lastSendMailTime = 0
    while(False) :
        subSendMailTime = GetSubSendMailTime(lastSendMailTime)
        lastSendMailTime = time.time()
        print('==> sleep begin...', subSendMailTime)
        time.sleep(subSendMailTime)

        strInfo = GetWeatherInfo("西安")
        strInfo += GetWeatherInfo("伊春")
        strInfo += GetWeiboRealtimeHotInfos()
        strInfo += GetHuangliInfo()
        SendMail(strInfo)
        print("==> send today(%d) info success" %lastSendMailTime)
    #print(GetSubSendMailTime(lastSendMailTime))
    #print(GetWeiboRealtimeHotInfos())


main()

?

呼~

关爱闹钟

人人有责