1

1_requests之百度图片批量获取.py

@@ -0,0 +1,116 @@
+import requests
+import os,random
+from urllib import request
+from multiprocessing import Pool
+'''
+#测试网站
+http://httpbin.org/get
+#代理网站
+'''
+url = 'https://image.baidu.com/search/acjson'
+headers = {
+    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.129 Safari/537.36'
+}
+
+
+
+
+def parse(kw,num):
+
+        infos = []
+        for i in range(30,30*num + 30,30):
+                try:
+                        params = {
+                                'tn': 'resultjson_com',
+                                'ipn': 'rj',
+                                'ct': '201326592',
+                                'is':'',
+                                'fp': 'result',
+                                'queryWord': kw,
+                                'cl': '2',
+                                'lm': '-1',
+                                'ie': 'utf-8',
+                                'oe': 'utf-8',
+                                'adpicid':'',
+                                'st':'',
+                                'z':'',
+                                'ic':'',
+                                'hd':'',
+                                'latest':'',
+                                'copyright':'',
+                                'word': kw,
+                                's':'',
+                                'se':'',
+                                'tab':'',
+                                'width':'',
+                                'height':'',
+                                'face':'',
+                                'istype':'',
+                                'qc':'',
+                                'nc':'',
+                                'fr':'',
+                                'expermode':'',
+                                'force':'',
+                                'cg': 'girl',
+                                'pn': str(i),
+                                'rn': '30',
+                                'gsm':'',
+                                '1600066985636':''
+                        }
+                        response = requests.get(url = url,headers = headers,params=params)
+                        datas = response.json()
+                        infos.append(datas)
+                except:
+                        continue
+        return infos
+# # print(datas['data'][0]['thumbURL'])
+#
+def down_loads(datas):
+        img_urls = []
+        for j in datas['data']:
+                try:
+                        img_url = j['thumbURL']
+                        img_urls.append(img_url)
+                except:
+                        continue
+
+
+        for url in img_urls:
+                 suffix = os.path.splitext(url)[1]
+                 img_name = str(random.randint(0,100000)) + suffix
+                 request.urlretrieve(url,r".\pic\\" + img_name)
+                 print(f'{img_name}已经下载完成！！！')
+
+
+def main():
+        kw = input('请输入你想下载的图片：')
+        po = Pool(10)
+        datas = parse(kw,20)
+        for data in datas:
+                po.apply_async(down_loads,args=(data,))
+        po.close()
+        po.join()
+
+
+if __name__ == '__main__':
+    main()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+