调整

download/文件下载.py

@@ -0,0 +1,27 @@
+import os
+from urllib.request import urlopen
+from tqdm import tqdm
+import requests
+import sys
+from threading import Thread,Lock
+lock = Lock()
+def download(url,filename=None):
+    file_size = int(requests.head(url).headers['Content-Length'])
+    if not filename:
+        filename = url.split('/')[-1]
+    if os.path.exists(filename):
+        first_byte = os.path.getsize(filename)
+        print('断点续传中。。。')
+    else:
+        first_byte = 0
+    header = {'Range': 'bytes=%s-%s' % (first_byte, file_size)}
+    pbar = tqdm(total=file_size,initial=first_byte,unit='B',unit_scale=True,desc=url.split('/')[-1],mininterval=0.5)
+    result = requests.get(url,headers = header,stream=True)
+    with open(filename,'ab') as f:
+        for chunk in result.iter_content(chunk_size=1024):
+            f.write(chunk)
+            pbar.update(1024)
+    pbar.close()
+    return file_size
+if __name__ == '__main__':
+    download('http://huo.hongjiaozuida.com/20200606/5381_8ab40c11/少年间谍第一季-08.mp4')

spider/doutu.py

@@ -1,39 +1,39 @@
-#!/usr/bin/env python3
-#_*_ coding: utf-8 _*_
-'''
-***********************************************
-authOr: newrain                               *
-blog:   https://blog.csdn.net/NewRain_wang    *
-        https://newrain001.gitee.io           *
-github: https://github.com/newrain001         *
-gitee : https://gitee.com/newrain001          *
-email : newrain_wang@163.com                  *
-***********************************************
-'''
-import requests
-from lxml import etree
-import time
-import os
-
-def getUrl():
-    header = {
-        'User-Agent': 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36',
-        'Referer': 'www.doutula.com',
-    }
-    html = requests.get('https://www.doutula.com/photo/list', headers=header)
-    if html.status_code == 200:
-        e = etree.HTML(html.text)
-        url = e.xpath('//ul/li/div/div/a/img/@data-original')
-        for i in url:
-            name = i.split("/")[-1]
-            result = requests.get(i)
-            if not os.path.exists('./image'):
-                os.mkdir('image')
-            with open(f'image/{name}', 'wb') as f:
-                f.write(result.content)
-            print(name,'已完成')
-            time.sleep(1)
-
-
-
+#!/usr/bin/env python3
+#_*_ coding: utf-8 _*_
+'''
+***********************************************
+authOr: newrain                               *
+blog:   https://blog.csdn.net/NewRain_wang    *
+        https://newrain001.gitee.io           *
+github: https://github.com/newrain001         *
+gitee : https://gitee.com/newrain001          *
+email : newrain_wang@163.com                  *
+***********************************************
+'''
+import requests
+from lxml import etree
+import time
+import os
+
+def getUrl():
+    header = {
+        'User-Agent': 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/93.0.4577.63 Safari/537.36',
+        'Referer': 'www.doutula.com',
+    }
+    html = requests.get('https://www.doutula.com/photo/list', headers=header)
+    if html.status_code == 200:
+        e = etree.HTML(html.text)
+        url = e.xpath('//ul/li/div/div/a/img/@data-original')
+        for i in url:
+            name = i.split("/")[-1]
+            result = requests.get(i)
+            if not os.path.exists('./image'):
+                os.mkdir('image')
+            with open(f'image/{name}', 'wb') as f:
+                f.write(result.content)
+            print(name,'已完成')
+            time.sleep(1)
+
+
+
 getUrl()