用 python 找出那些被“标记”的照片

● python3.6

● requests

● exifread

1. 遍历目录

2. 拉取数据集合

3. 遍历集合取得exif

4. exif信息整理，并获取实体地址

5. 拷贝文件到结果样本目录

6. 生成json报告文件

{

"GPSVersionID": "GPS版本",

"GPSLatitudeRef": "南北纬",

"GPSLatitude": "纬度",

"GPSLongitudeRef": "东西经",

"GPSLongitude": "经度",

"GPSAltitudeRef": "海拔参照值",

"GPSAltitude": "海拔",

"GPSTimeStamp": "GPS时间戳",

"GPSSatellites": "测量的卫星",

"GPSStatus": "接收器状态",

"GPSMeasureMode": "测量模式",

"GPSDOP": "测量精度",

"GPSSpeedRef": "速度单位",

"GPSSpeed": "GPS接收器速度",

"GPSTrackRef": "移动方位参照",

"GPSTrack": "移动方位",

"GPSImgDirectionRef": "图像方位参照",

"GPSImgDirection": "图像方位",

"GPSMapDatum": "地理测量资料",

"GPSDestLatitudeRef": "目标纬度参照",

"GPSDestLatitude": "目标纬度",

"GPSDestLongitudeRef": "目标经度参照",

"GPSDestLongitude": "目标经度",

"GPSDestBearingRef": "目标方位参照",

"GPSDestBearing": "目标方位",

"GPSDestDistanceRef": "目标距离参照",

"GPSDestDistance": "目标距离",

"GPSProcessingMethod": "GPS处理方法名",

"GPSAreaInformation": "GPS区功能变数名",

"GPSDateStamp": "GPS日期",

"GPSDifferential": "GPS修正"

}

import os

import time

import json

import random

import logging

import requests

import exifread

logging.basicConfig(level=logging.CRITICAL)

KEY = "169d2dd7829fe45690fabec812d05bc3"

def main():

# 预设后缀列表

types = ["bmp", "jpg", "tiff", "gif", "png"]

#结果数据集合

picex = []

# 文件存储路径

saves = "$" + input("| SavePath: ").strip()

# 文件搜索路径 并遍历所有文件返回文件路径列表

pools = jpgwalk(input("| FindPath: "), types)

#存储目录

savep = "%s/%s" % (os.getcwd().replace("\\", "/"), saves)

if savep in pools:

pools.remove(savep)

# 遍历数据集并获取exif信息

for path in pools:

res = getEXIF(path)

if res:

picex.append(res)

# 结果报告

print("| Result %s" % len(picex))

# 如果存在结果 保存结果到json并讲相关图片复制到该目录下

if picex:

#创建目录

if not os.path.exists(saves):

os.mkdir(saves)

#生成一个4格缩进的json文件

with open("%s/%s.json" % (saves, saves), "wb") as f:

f.write(json.dumps(picex, ensure_ascii=False, indent=4).encode("utf8"))

#copy图像到该目录

for item in picex:

source_path = item["Filename"]

with open("%s/%s" % (saves, source_path.split("/")[-1]), "wb") as f_in:

with open(source_path, "rb") as f_out:

f_in.write(f_out.read())

def main():

# 预设后缀列表

types = ["bmp", "jpg", "tiff", "gif", "png"]

#结果数据集合

picex = []

# 文件存储路径

saves = "$" + input("| SavePath: ").strip()

# 文件搜索路径 并遍历所有文件返回文件路径列表

pools = jpgwalk(input("| FindPath: "), types)

#存储目录

savep = "%s/%s" % (os.getcwd().replace("\\", "/"), saves)

if savep in pools:

pools.remove(savep)

# 遍历数据集并获取exif信息

for path in pools:

res = getEXIF(path)

if res:

picex.append(res)

# 结果报告

print("| Result %s" % len(picex))

# 如果存在结果 保存结果到json并讲相关图片复制到该目录下

if picex:

#创建目录

if not os.path.exists(saves):

os.mkdir(saves)

#生成一个4格缩进的json文件

with open("%s/%s.json" % (saves, saves), "wb") as f:

f.write(json.dumps(picex, ensure_ascii=False, indent=4).encode("utf8"))

#copy图像到该目录

for item in picex:

source_path = item["Filename"]

with open("%s/%s" % (saves, source_path.split("/")[-1]), "wb") as f_in:

with open(source_path, "rb") as f_out:

f_in.write(f_out.read())

def cg(i):

try:

_ii = [float(eval(x)) for x in i[1:][:-1].split(', ')]

_res = _ii[0] + _ii[1] / 60 + _ii[2] / 3600

return _res

except ZeroDivisionError:

return 0

def getEXIF(filepath):

#基础关键字

_showlist = [

'GPS GPSDOP',

'GPS GPSMeasureMode',

'GPS GPSAltitudeRef',

'GPS GPSAltitude',

'Image Software',

'Image Model',

'Image Make'

]

#GPS关键字

_XYlist = ["GPS GPSLatitude", "GPS GPSLongitude"]

#时间关键字

_TimeList = ["EXIF DateTimeOrigina", "Image DateTime", "GPS GPSDate"]

#初始化结果字典

_infos = {

'Filename': filepath

}

with open(filepath, "rb") as _files:

_tags = None

# 尝试去的EXIF信息

try:

_tags = exifread.process_file(_files)

except KeyError:

return

# 判断是否存在地理位置信息

_tagkeys = _tags.keys()

if _tags and len(set(_tagkeys) & set(_XYlist)) == 2 and cg(str(_tags["GPS GPSLongitude"])) != 0.0:

for _item in sorted(_tagkeys):

if _item in _showlist:

_infos[_item.split()[-1]] = str(_tags[_item]).strip()

# 经纬度取值

_infos["GPS"] = (cg(str(_tags["GPS GPSLatitude"])) * float(1.0 if str(_tags.get("GPS GPSLatitudeRef", "N")) == "N" else -1.0),

cg(str(_tags["GPS GPSLongitude"])) * float(1.0 if str(_tags.get("GPS GPSLongitudeRef", "E")) == "E" else -1.0))

# 获取实体地址

_infos["address"] = address(_infos["GPS"])

# 获取照片海拔高度

if "GPS GPSAltitudeRef" in _tagkeys:

try:

_infos["GPSAltitude"] = eval(_infos["GPSAltitude"])

except ZeroDivisionError:

_infos["GPSAltitude"] = 0

_infos["GPSAltitude"] = "距%s%.2f米" % ("地面" if int(

_infos["GPSAltitudeRef"]) == 1 else "海平面", _infos["GPSAltitude"])

del _infos["GPSAltitudeRef"]

# 获取可用时间

_timeitem = list(set(_TimeList) & set(_tagkeys))

if _timeitem:

_infos["Dates"] = str(_tags[_timeitem[0]])

return _infos

def address(gps):

global KEY

try:

# 随机UA

_ulist = [

"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1",

"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0",

"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; InfoPath.2; .NET4.0C; .NET4.0E; .NET CLR 2.0.50727; 360SE)",

"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11",

"Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",

"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Win64; x64; Trident/5.0; .NET CLR 2.0.50727; SLCC2; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.3; .NET4.0C; Tablet PC 2.0; .NET4.0E)",

"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)",

"Mozilla/5.0 (X11; U; Linux i686; rv:1.7.3) Gecko/20040913 Firefox/0.10",

"Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; ja) Presto/2.10.289 Version/12.00",

"Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.93 Safari/537.36"

]

# 伪造header

_header = {

"User-Agent": random.choice(_ulist),

"Accept": "text/javascript, application/javascript, application/ecmascript, application/x-ecmascript, */*; q=0.01",

"Accept-Encoding": "gzip, deflate, sdch",

"Accept-Language": "zh-CN,zh;q=0.8",

"Referer": "http://www.gpsspg.com",

}

_res = requests.get(

"http://restapi.amap.com/v3/geocode/regeo?key={2}&s=rsv3&location={1},{0}&platform=JS&logversion=2.0&sdkversion=1.3&appname=http%3A%2F%2Fwww.gpsspg.com%2Fiframe%2Fmaps%2Famap_161128.htm%3Fmapi%3D3&csid=945C5A2C-E67F-4362-B881-9608D9BC9913".format(gps[0], gps[1], KEY), headers=_header, timeout=(5, 5))

_json = _res.json()

# 判断是否取得数据

if _json and _json["status"] == "1" and _json["info"] == "OK":

# 返回对应地址

return _json.get("regeocode").get("formatted_address")

except Exception as e:

pass