提交代码

Author: cxhuan

.DS_Store

@@ -0,0 +1,75 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+import json
+import re
+
+import exifread
+import requests
+
+
+#转换经纬度格式
+def convert_coor(*arg):
+    return float(arg[0]) + ((float(arg[1]) + (float(arg[2].split('/')[0]) / float(arg[2].split('/')[-1]) / 60)) / 60)
+
+# 读取照片的GPS经纬度信息
+def extract_image(pic_path):
+    GPS = {}
+    date = ''
+    with open(pic_path, 'rb') as f:
+        tags = exifread.process_file(f)
+        for tag, value in tags.items():
+            # 纬度
+            if re.match('GPS GPSLatitudeRef', tag):
+                GPS['GPSLatitudeRef'] = str(value)
+            # 经度
+            elif re.match('GPS GPSLongitudeRef', tag):
+                GPS['GPSLongitudeRef'] = str(value)
+            # 海拔
+            elif re.match('GPS GPSAltitudeRef', tag):
+                GPS['GPSAltitudeRef'] = str(value)
+            elif re.match('GPS GPSLatitude', tag):
+                try:
+                    match_result = re.match('\[(\w*),(\w*),(\w.*)/(\w.*)\]', str(value)).groups()
+                    GPS['GPSLatitude'] = int(match_result[0]), int(match_result[1]), int(match_result[2])
+                except:
+                    deg, min, sec = [x.replace(' ', '') for x in str(value)[1:-1].split(',')]
+                    GPS['GPSLatitude'] = convert_coor(deg, min, sec)
+            elif re.match('GPS GPSLongitude', tag):
+                try:
+                    match_result = re.match('\[(\w*),(\w*),(\w.*)/(\w.*)\]', str(value)).groups()
+                    GPS['GPSLongitude'] = int(match_result[0]), int(match_result[1]), int(match_result[2])
+                except:
+                    deg, min, sec = [x.replace(' ', '') for x in str(value)[1:-1].split(',')]
+                    GPS['GPSLongitude'] = convert_coor(deg, min, sec)
+            elif re.match('GPS GPSAltitude', tag):
+                GPS['GPSAltitude'] = str(value)
+            elif re.match('.*Date.*', tag):
+                date = str(value)
+    return {'GPS_information': GPS, 'date_information': date}
+
+
+# 通过baidu Map的API将GPS信息转换成地址
+def find_address_from_bd(GPS):
+    secret_key = 'wLyevcXk5QY36hTKmvV5350F'
+    if not GPS['GPS_information']:
+        return '该照片无GPS信息'
+    lat, lng = GPS['GPS_information']['GPSLatitude'], GPS['GPS_information']['GPSLongitude']
+    baidu_map_api = "http://api.map.baidu.com/geocoder/v2/?ak={0}&callback=renderReverse&location={1},{2}s&output=json&pois=0".format(
+        secret_key, lat, lng)
+    response = requests.get(baidu_map_api)
+    content = response.text.replace("renderReverse&&renderReverse(", "")[:-1]
+    baidu_map_address = json.loads(content)
+    formatted_address = baidu_map_address["result"]["formatted_address"]
+    province = baidu_map_address["result"]["addressComponent"]["province"]
+    city = baidu_map_address["result"]["addressComponent"]["city"]
+    district = baidu_map_address["result"]["addressComponent"]["district"]
+    location = baidu_map_address["result"]["sematic_description"]
+    return formatted_address, province, city, district, location
+
+
+if __name__ == '__main__':
+    gpsinfo = extract_image(pic_path='/Users/xxx/Pictures/66.jpg')
+    address = find_address_from_bd(GPS=gpsinfo)
+    print(gpsinfo)
+    print("拍摄时间：" + gpsinfo.get("date_information"))
+    print('照片拍摄地址:' + str(address))

xianhuan/.DS_Store

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+@author: 闲欢
+"""
+
+import requests
+import re
+import os
+import time
+cookie = {
+    'Cookie': 'your cookie'
+}
+header = {
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4144.2 Safari/537.36'
+}
+get_order = input('是否启动程序? yes or no:   ')
+number = 1
+store_path = 'your path'
+while True:
+    if get_order != 'no':
+        print('抓取中......')  # 下面的链接填写微博搜索的链接
+        url = f'https://s.weibo.com/weibo?q=%23%E5%B0%91%E5%A5%B3%E5%86%99%E7%9C%9F%23&wvr=6&b=1&Refer=SWeibo_box&page={number}'
+        response = requests.get(url, cookies=cookie)
+        result = response.text
+        print(result)
+        detail = re.findall('data="uid=(.*?)&mid=(.*?)&pic_ids=(.*?)">', result)
+        for part in detail:
+            uid = part[0]
+            mid = part[1]
+            pids = part[2]
+            for picid in pids.split(','):
+                url_x = f'https://wx1.sinaimg.cn/large/%s.jpg'%picid  # 这里就是大图链接了
+                response_photo = requests.get(url_x, headers=header)
+                file_name = url_x[-10:]
+                if not os.path.exists(store_path+uid):
+                    os.mkdir(store_path+uid)
+                with open(store_path+uid + '/' + file_name, 'ab') as f:  # 保存文件
+                    f.write(response_photo.content)
+                    time.sleep(0.5)
+        print('获取完毕')
+        get_order = input('是否继续获取下一页? Y:yes N:no:   ')
+        if get_order != 'no':
+            number += 1
+        else:
+            print('程序结束')
+            break
+    else:
+        print('程序结束')
+        break