feat:1.编写自由时报爬虫脚本

2.编写数据量统计脚本

pc_ltn.py

@@ -57,7 +57,7 @@ def reptile(browser=None, search_word=""):
     # 循环分页
     for key, element in enumerate(page_list_element):
 
-        if key > 0 or key <= len(page_list_element) - 1:
+        if key > 0 and key <= len(page_list_element) - 1:
             # 点击分页
             browser.get(f"{url}&page={key+1}")
             # element.click()
@@ -90,7 +90,11 @@ def reptile(browser=None, search_word=""):
                     # 访问地址
                     access_address = f'{get_base_file_url()}{table_name.split("_")[1]}/{local_path_name}/{id}.jpg'
                     # 下载状态
-                    status = download_image(element['src'], download_dir)
+                    if "default" in element['src']:
+                        status = False
+                    else:
+                        status = download_image(element['src'], download_dir)
+
                     if status:
                         # element['src'] = access_address
                         img_tag["src"] = access_address

utils/index.py

@@ -137,8 +137,8 @@ def parse_ltn_time_string(time_str):
         except ValueError:
             return None
     else:
-        # print(time_str)
-        return datetime.datetime.strptime(time_str, '%Y/%m/%d')
+        dt_object = datetime.datetime.strptime(time_str, '%Y/%m/%d')
+        return dt_object.timestamp()
 
 
 # 转换 youtube 的时间