python 爬取天气网卫星图片
更新时间:2021年06月07日 15:02:13 作者:MrWayneLee
根据网站URL的规律编写的一个爬取天气网卫星图片的python爬虫,使用了requests包,感兴趣的朋友可以参考下
项目地址:
https://github.com/MrWayneLee/weather-demo
代码部分
下载生成文件功能
# 下载并生成文件 def downloadImg(imgDate, imgURLs, pathName): a,s,f = 0,0,0 timeStart = time.time() while a < len(imgURLs): req = requests.get(imgURLs[a]) imgName = str(imgURLs[a])[-13:-9] print(str("开始请求" + imgDate + " " + imgName + "的数据")) if req.status_code == 200: open(pathName + '\\' + os.path.basename(imgName) + '.png', 'wb').write(req.content) print("数据" + imgDate + " " + imgName + "下载完成") s += 1 del req elif req.status_code == 404: print("数据" + imgDate + " " + imgName + "不存在") f += 1 a += 1 timeEnd = time.time() totalTime = round(timeEnd - timeStart, 2) print("全部数据请求完成!总耗时:",totalTime,"秒") print("共请求", a, "次;成功", s, "次;失败", f, "次")
创建文件夹
def createFolder(pathName): imgName_Year = pathName[0:4] imgName_Month = pathName[4:6] imgName_Day = pathName[6:8] imgName_date = imgName_Year + '-' + imgName_Month + '-' + imgName_Day mainPath = 'F:\\[Wayne Lee]\\学习资料\\Python\\爬取图像' newPathName = mainPath + '\\' + imgName_date realPath = newPathName + '\\' isExists = os.path.exists(newPathName) if not isExists: os.makedirs(newPathName) print("新文件夹 [" + imgName_date + "] 创建成功") return realPath else: print(pathName + "文件夹已存在") return realPath
生成时间列表
def generateTime(imgUrl): timeList = [] imgUrlList = [] h,j = 0,0 while h < 24: m = 0 while m < 60: timeList.append("{:0>4d}".format(h * 100 + m)) m += 15 h += 1 # print(timeList) # print(len(timeList)) while j < len(timeList): imgUrlList.append(str(imgUrl + timeList[j] + "00000.JPG")) # print(timeList[j]) j += 1 return imgUrlList # print(imgUrlList) # print(len(imgUrlList))
生成下载URL列表
def downloadUrl(imgDate): imgUrl = "http://image.nmc.cn/product/" + imgDate[0:4] + "/" + imgDate[4:6] + "/" + imgDate[6:8] + "/WXBL/SEVP_NSMC_WXBL_FY4A_ETCC_ACHN_LNO_PY_" + imgDate # + "0000" +"00000.JPG" URLlist = list(generateTime(imgUrl)) return URLlist
主函数
# 主函数 if __name__ == '__main__': # imgUrl = "http://image.nmc.cn/product/2020/04/11/WXBL/SEVP_NSMC_WXBL_FY4A_ETCC_ACHN_LNO_PY_20200411044500000.JPG" # imgUrl = "http://image.nmc.cn/product/2020/04/11/WXBL/SEVP_NSMC_WXBL_FY4A_ETCC_ACHN_LNO_PY_20200411" # imgName = imgUrl[-21:-9] while True: print("[1]手动输入日期") print("[2]获取当天日期") print("[3]退出程序") choose = str(input("你的选择:")) if choose == "1": imgDate = str(input("请输入日期[如20200411]:")) urlList = list(downloadUrl(imgDate)) break elif choose == "2": imgDate = time.strftime("%Y%m%d",time.localtime()) urlList = list(downloadUrl(imgDate)) break elif choose == "3": break else: print("你的选择有误!请重试")
开始下载
pathName = createFolder(imgDate) # 开始下载 downloadImg(imgDate, urlList, pathName)
完整代码
import requests import time import datetime import os # 下载并生成文件 def downloadImg(imgDate, imgURLs, pathName): a,s,f = 0,0,0 timeStart = time.time() while a < len(imgURLs): req = requests.get(imgURLs[a]) imgName = str(imgURLs[a])[-13:-9] print(str("开始请求" + imgDate + " " + imgName + "的数据")) if req.status_code == 200: open(pathName + '\\' + os.path.basename(imgName) + '.png', 'wb').write(req.content) print("数据" + imgDate + " " + imgName + "下载完成") s += 1 del req elif req.status_code == 404: print("数据" + imgDate + " " + imgName + "不存在") f += 1 a += 1 timeEnd = time.time() totalTime = round(timeEnd - timeStart, 2) print("全部数据请求完成!总耗时:",totalTime,"秒") print("共请求", a, "次;成功", s, "次;失败", f, "次") # 创建文件夹 def createFolder(pathName): imgName_Year = pathName[0:4] imgName_Month = pathName[4:6] imgName_Day = pathName[6:8] imgName_date = imgName_Year + '-' + imgName_Month + '-' + imgName_Day mainPath = 'F:\\[Wayne Lee]\\学习资料\\Python\\爬取图像' newPathName = mainPath + '\\' + imgName_date realPath = newPathName + '\\' isExists = os.path.exists(newPathName) if not isExists: os.makedirs(newPathName) print("新文件夹 [" + imgName_date + "] 创建成功") return realPath else: print(pathName + "文件夹已存在") return realPath # 生成时间列表 def generateTime(imgUrl): timeList = [] imgUrlList = [] h,j = 0,0 while h < 24: m = 0 while m < 60: timeList.append("{:0>4d}".format(h * 100 + m)) m += 15 h += 1 # print(timeList) # print(len(timeList)) while j < len(timeList): imgUrlList.append(str(imgUrl + timeList[j] + "00000.JPG")) # print(timeList[j]) j += 1 return imgUrlList # print(imgUrlList) # print(len(imgUrlList)) # 生成下载URL列表 def downloadUrl(imgDate): imgUrl = "http://image.nmc.cn/product/" + imgDate[0:4] + "/" + imgDate[4:6] + "/" + imgDate[6:8] + "/WXBL/SEVP_NSMC_WXBL_FY4A_ETCC_ACHN_LNO_PY_" + imgDate # + "0000" +"00000.JPG" URLlist = list(generateTime(imgUrl)) return URLlist # 主函数 if __name__ == '__main__': # imgUrl = "http://image.nmc.cn/product/2020/04/11/WXBL/SEVP_NSMC_WXBL_FY4A_ETCC_ACHN_LNO_PY_20200411044500000.JPG" # imgUrl = "http://image.nmc.cn/product/2020/04/11/WXBL/SEVP_NSMC_WXBL_FY4A_ETCC_ACHN_LNO_PY_20200411" # imgName = imgUrl[-21:-9] while True: print("[1]手动输入日期") print("[2]获取当天日期") print("[3]退出程序") choose = str(input("你的选择:")) if choose == "1": imgDate = str(input("请输入日期[如20200411]:")) urlList = list(downloadUrl(imgDate)) break elif choose == "2": imgDate = time.strftime("%Y%m%d",time.localtime()) urlList = list(downloadUrl(imgDate)) break elif choose == "3": break else: print("你的选择有误!请重试") # 创建文件夹 pathName = createFolder(imgDate) # 开始下载 downloadImg(imgDate, urlList, pathName)
爬取效果
以上就是python 爬取天气网卫星图片的详细内容,更多关于python 爬取天气网图片的资料请关注脚本之家其它相关文章!
相关文章
利用Python-iGraph如何绘制贴吧/微博的好友关系图详解
这篇文章主要给大家介绍了关于利用Python-iGraph如何绘制贴吧/微博好友关系图的相关资料,文中显示介绍了在windows系统下安装python-igraph的步骤,然后通过示例代码演示了绘制好友关系图的方法,需要的朋友可以参考下。2017-11-11python爬虫爬取淘宝商品比价(附淘宝反爬虫机制解决小办法)
这篇文章主要介绍了python爬虫爬取淘宝商品比价(附淘宝反爬虫机制解决小办法),文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧2020-12-12
最新评论