目录
- 项目地址：
- 代码部分
- 下载生成文件功能
- 创建文件夹
- 生成时间列表
- 生成下载URL列表
- 主函数
- 爬取效果
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！
您可能感兴趣的文章:- 基于Python实现ComicReaper漫画自动爬取脚本过程解析
- Python爬虫实战之爬取京东商品数据并实实现数据可视化
- 高考要来啦!用Python爬取历年高考数据并分析
- Python爬虫实战之使用Scrapy爬取豆瓣图片
- 只用50行Python代码爬取网络美女高清图片
- 再也不用花钱买漫画!Python爬取某漫画的脚本及源码
