heyudev преди 2 години
родител
ревизия
894b2abf37
променени са 14 файла, в които са добавени 58 реда и са изтрити 1 реда
  1. 1 1
      .gitignore
  2. 0 0
      crawler/__init__.py
  3. 1 0
      crawler/alert.py
  4. 1 0
      crawler/auth.py
  5. 21 0
      crawler/config.py
  6. 22 0
      crawler/run.py
  7. 0 0
      crawler/shipinhao/__init__.py
  8. 1 0
      crawler/utils.py
  9. 1 0
      crawler/video.py
  10. 0 0
      crawler/xiaoniangao/__init__.py
  11. 0 0
      docs/Makefile
  12. 0 0
      docs/requirements.txt
  13. 0 0
      tests/__init__.py
  14. 10 0
      tests/video.py

+ 1 - 1
.gitignore

@@ -51,7 +51,7 @@ coverage.xml
 
 # Django stuff:
 *.log
-
+.idea/
 # Sphinx documentation
 docs/_build/
 

+ 0 - 0
crawler/__init__.py


+ 1 - 0
crawler/alert.py

@@ -0,0 +1 @@
+# 报警

+ 1 - 0
crawler/auth.py

@@ -0,0 +1 @@
+# 鉴权 :session cookie 处理

+ 21 - 0
crawler/config.py

@@ -0,0 +1,21 @@
+# 配置信息:环境 策略等
+
+
+class Config:
+    ENV = {
+        'dev': 'dev',  # 开发环境
+        'test': 'test',  # 开发环境
+        'pre': 'pre',  # 开发环境
+        'prod': 'prod'  # 开发环境
+    }
+    PLATFORM = {
+        'xiaoniangao': 'xiaoniangao',  # 小年糕
+        'xigua': 'xigua',  # 西瓜视频
+        'shipinhao': 'shipinhao'  # 视频号
+    }
+
+    STRATEGY = {
+        'channel_page': 'channel_page',  # 推荐/频道页  规则抓取
+        'home_page': 'home_page',  # 用户主页 规则抓取
+        'search': 'search'  # 搜索结果 规则抓取
+    }

+ 22 - 0
crawler/run.py

@@ -0,0 +1,22 @@
+import logging
+import sys
+
+from crawler import config
+
+
+class Main:
+    @staticmethod
+    def main(argv):
+        # Platform  Strategy  Env
+        print("start run crawler...")
+        print("Platform = " + argv[0])
+        print("Strategy = " + argv[1])
+        print("Env = " + argv[2])
+        print("Platform = " + config.PLATFORM['xiaoniangao'])
+        print("Strategy = " + config.STRATEGY['home_page'])
+        print("Env = " + config.ENV['test'])
+
+
+
+if __name__ == '__main__':
+    Main.main(sys.argv)

+ 0 - 0
crawler/shipinhao/__init__.py


+ 1 - 0
crawler/utils.py

@@ -0,0 +1 @@
+# 操作工具

+ 1 - 0
crawler/video.py

@@ -0,0 +1 @@
+# 核心流程:获取信息 ->

+ 0 - 0
crawler/xiaoniangao/__init__.py


+ 0 - 0
docs/Makefile


+ 0 - 0
docs/requirements.txt


+ 0 - 0
tests/__init__.py


+ 10 - 0
tests/video.py

@@ -0,0 +1,10 @@
+import unittest
+
+# 单元测试
+class MyTestCase(unittest.TestCase):
+    def test_something(self):
+        self.assertEqual(True, False)  # add assertion here
+
+
+if __name__ == '__main__':
+    unittest.main()