Update start.py

修正了若干常见问题

start.py

@@ -8,8 +8,7 @@ from time import sleep
 
 """
 本项目开源地址 https://github.com/LeLe86/vWeChatCrawl
-讨论QQ群 703431832
-
+讨论QQ群 703431832 加群暗号:不止技术流
 """
 
 #保存文件
@@ -51,8 +50,9 @@ def DownLoadHtml(url):
                      'Connection':'keep-alive',
                      'Accept-Language':'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3'
               }
-    requests.packages.urllib3.disable_warnings()
-    response = requests.get(url,headers = headers,proxies=None,verify=False)
+    session = requests.Session()
+    session.trust_env = False
+    response = session.get(url,headers = headers)
     if response.status_code == 200:
         htmltxt = response.text #返回的网页正文
         return htmltxt
@@ -68,10 +68,11 @@ def DownImg(url,savepath):
                      'Connection':'keep-alive',
                      'Accept-Language':'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3'
               }
-    requests.packages.urllib3.disable_warnings()
-    r = requests.get(url,headers = headers,proxies=None,verify=False)
+    session = requests.Session()
+    session.trust_env = False
+    response = session.get(url, headers=headers)
     with open(savepath, 'wb') as f:
-        f.write(r.content)
+        f.write(response.content)
 
 #修改网页中图片的src，使图片能正常显示
 def ChangeImgSrc(htmltxt,saveimgdir,htmlname):
@@ -89,7 +90,7 @@ def ChangeImgSrc(htmltxt,saveimgdir,htmlname):
             originalURL = ""
         if originalURL.startswith("//"):#如果url以//开头，则需要添加http：
             originalURL = "http:" + originalURL
-        if len(originalURL) > 0:
+        if len(originalURL) > 20:
             print("\r down imgs " + "▇" * imgindex +"  " + str(imgindex),end="")
             if "data-type" in img.attrs:
                 imgtype = img.attrs["data-type"]
@@ -133,6 +134,7 @@ def GetArticleList(jsondir):
     filelist = os.listdir(jsondir)
     ArtList = []
     for file in filelist:
+        try:
             filepath = os.path.join(jsondir,file)
             filetxt = ReadFile(filepath)
             jsbody = json.loads(filetxt)
@@ -165,6 +167,8 @@ def GetArticleList(jsondir):
                           if len(url)>3:
                             ArtList.append(art)
                           print(len(ArtList),pubdate, idx, title)
+        except:
+            print("跳过，可不用管",file)
     return ArtList
 
 def DownHtmlMain(jsonDir,saveHtmlDir):