目錄
- 項目地址：
- 代碼部分
- 下載生成文件功能
- 創建文件夾
- 生成時間列表
- 生成下載URL列表
- 主函數
- 爬取效果
項目地址：
https://github.com/MrWayneLee/weather-demo
代碼部分
下載生成文件功能
# 下載并生成文件
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("開始請求" + imgDate + " " + imgName + "的數據"))
if req.status_code == 200:
open(pathName + '\\' + os.path.basename(imgName) + '.png', 'wb').write(req.content)
print("數據" + imgDate + " " + imgName + "下載完成")
s += 1
del req
elif req.status_code == 404:
print("數據" + imgDate + " " + imgName + "不存在")
f += 1
a += 1
timeEnd = time.time()
totalTime = round(timeEnd - timeStart, 2)
print("全部數據請求完成！總耗時：",totalTime,"秒")
print("共請求", a, "次；成功", s, "次；失敗", f, "次")
創建文件夾
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]\\學習資料\\Python\\爬取圖像'
newPathName = mainPath + '\\' + imgName_date
realPath = newPathName + '\\'
isExists = os.path.exists(newPathName)
if not isExists:
os.makedirs(newPathName)
print("新文件夾 [" + imgName_date + "] 創建成功")
return realPath
else:
print(pathName + "文件夾已存在")
return realPath
生成時間列表
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))
生成下載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
主函數
# 主函數
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]手動輸入日期")
print("[2]獲取當天日期")
print("[3]退出程序")
choose = str(input("你的選擇："))
if choose == "1":
imgDate = str(input("請輸入日期[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("你的選擇有誤！請重試")
開始下載
pathName = createFolder(imgDate)
# 開始下載
downloadImg(imgDate, urlList, pathName)
完整代碼
import requests
import time
import datetime
import os
# 下載并生成文件
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("開始請求" + imgDate + " " + imgName + "的數據"))
if req.status_code == 200:
open(pathName + '\\' + os.path.basename(imgName) + '.png', 'wb').write(req.content)
print("數據" + imgDate + " " + imgName + "下載完成")
s += 1
del req
elif req.status_code == 404:
print("數據" + imgDate + " " + imgName + "不存在")
f += 1
a += 1
timeEnd = time.time()
totalTime = round(timeEnd - timeStart, 2)
print("全部數據請求完成！總耗時：",totalTime,"秒")
print("共請求", a, "次；成功", s, "次；失敗", f, "次")
# 創建文件夾
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]\\學習資料\\Python\\爬取圖像'
newPathName = mainPath + '\\' + imgName_date
realPath = newPathName + '\\'
isExists = os.path.exists(newPathName)
if not isExists:
os.makedirs(newPathName)
print("新文件夾 [" + imgName_date + "] 創建成功")
return realPath
else:
print(pathName + "文件夾已存在")
return realPath
# 生成時間列表
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))
# 生成下載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
# 主函數
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]手動輸入日期")
print("[2]獲取當天日期")
print("[3]退出程序")
choose = str(input("你的選擇："))
if choose == "1":
imgDate = str(input("請輸入日期[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("你的選擇有誤！請重試")
# 創建文件夾
pathName = createFolder(imgDate)
# 開始下載
downloadImg(imgDate, urlList, pathName)
爬取效果
以上就是python 爬取天氣網衛星圖片的詳細內容，更多關于python 爬取天氣網圖片的資料請關注腳本之家其它相關文章！
您可能感興趣的文章:- 基于Python實現ComicReaper漫畫自動爬取腳本過程解析
- Python爬蟲實戰之爬取京東商品數據并實實現數據可視化
- 高考要來啦!用Python爬取歷年高考數據并分析
- Python爬蟲實戰之使用Scrapy爬取豆瓣圖片
- 只用50行Python代碼爬取網絡美女高清圖片
- 再也不用花錢買漫畫!Python爬取某漫畫的腳本及源碼
