coocan 0.4.6__tar.gz → 0.4.7__tar.gz

coocan-0.4.7/PKG-INFO

@@ -0,0 +1,90 @@
+Metadata-Version: 2.1
+Name: coocan
+Version: 0.4.7
+Summary: Air Spider Framework
+Author: wauo
+Author-email: markadc@126.com
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+
+# 项目说明
+
+- 一个非常轻量的异步爬虫框架
+
+# 项目地址
+
+- https://github.com/markadc/coocan
+
+## demo
+
+- 效果
+  <br>
+  ![效果](coocan/demo.gif)
+
+
+- 代码
+
+```python
+import json
+
+from loguru import logger
+
+import coocan
+from coocan import Request, MiniSpider
+
+
+class CSDNDetailSpider(MiniSpider):
+    start_urls = ['http://www.csdn.net']
+    max_requests = 10
+
+    def middleware(self, request: Request):
+        request.headers["Referer"] = "http://www.csdn.net/"
+
+    def parse(self, response):
+        api = "https://blog.csdn.net/community/home-api/v1/get-business-list"
+        params = {
+            "page": "1",
+            "size": "20",
+            "businessType": "lately",
+            "noMore": "false",
+            "username": "markadc"
+        }
+        yield Request(api, self.parse_page, params=params, cb_kwargs={"api": api, "params": params})
+
+    def parse_page(self, response, api, params):
+        current_page = params["page"]
+        data = json.loads(response.text)
+        some = data["data"]["list"]
+
+        if not some:
+            logger.warning("没有第 {} 页".format(current_page))
+            return
+
+        for one in some:
+            date = one["formatTime"]
+            name = one["title"]
+            detail_url = one["url"]
+            logger.info(
+                """
+                {} 
+                {} 
+                {}
+                """.format(date, name, detail_url)
+            )
+            yield coocan.Request(detail_url, self.parse_detail, cb_kwargs={"title": name})
+
+        logger.info("第 {} 页抓取成功".format(params["page"]))
+
+        # 抓取下一页
+        next_page = int(current_page) + 1
+        params["page"] = str(next_page)
+        yield Request(api, self.parse_page, params=params, cb_kwargs={"api": api, "params": params})
+
+    def parse_detail(self, response, title):
+        logger.success("{}  已访问 {}".format(response.status_code, title))
+
+
+if __name__ == '__main__':
+    s = CSDNDetailSpider()
+    s.go()
+```

coocan-0.4.7/README.md

@@ -0,0 +1,81 @@
+# 项目说明
+
+- 一个非常轻量的异步爬虫框架
+
+# 项目地址
+
+- https://github.com/markadc/coocan
+
+## demo
+
+- 效果
+  <br>
+  ![效果](coocan/demo.gif)
+
+
+- 代码
+
+```python
+import json
+
+from loguru import logger
+
+import coocan
+from coocan import Request, MiniSpider
+
+
+class CSDNDetailSpider(MiniSpider):
+    start_urls = ['http://www.csdn.net']
+    max_requests = 10
+
+    def middleware(self, request: Request):
+        request.headers["Referer"] = "http://www.csdn.net/"
+
+    def parse(self, response):
+        api = "https://blog.csdn.net/community/home-api/v1/get-business-list"
+        params = {
+            "page": "1",
+            "size": "20",
+            "businessType": "lately",
+            "noMore": "false",
+            "username": "markadc"
+        }
+        yield Request(api, self.parse_page, params=params, cb_kwargs={"api": api, "params": params})
+
+    def parse_page(self, response, api, params):
+        current_page = params["page"]
+        data = json.loads(response.text)
+        some = data["data"]["list"]
+
+        if not some:
+            logger.warning("没有第 {} 页".format(current_page))
+            return
+
+        for one in some:
+            date = one["formatTime"]
+            name = one["title"]
+            detail_url = one["url"]
+            logger.info(
+                """
+                {} 
+                {} 
+                {}
+                """.format(date, name, detail_url)
+            )
+            yield coocan.Request(detail_url, self.parse_detail, cb_kwargs={"title": name})
+
+        logger.info("第 {} 页抓取成功".format(params["page"]))
+
+        # 抓取下一页
+        next_page = int(current_page) + 1
+        params["page"] = str(next_page)
+        yield Request(api, self.parse_page, params=params, cb_kwargs={"api": api, "params": params})
+
+    def parse_detail(self, response, title):
+        logger.success("{}  已访问 {}".format(response.status_code, title))
+
+
+if __name__ == '__main__':
+    s = CSDNDetailSpider()
+    s.go()
+```

coocan-0.4.7/coocan.egg-info/PKG-INFO

@@ -0,0 +1,90 @@
+Metadata-Version: 2.1
+Name: coocan
+Version: 0.4.7
+Summary: Air Spider Framework
+Author: wauo
+Author-email: markadc@126.com
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+
+# 项目说明
+
+- 一个非常轻量的异步爬虫框架
+
+# 项目地址
+
+- https://github.com/markadc/coocan
+
+## demo
+
+- 效果
+  <br>
+  ![效果](coocan/demo.gif)
+
+
+- 代码
+
+```python
+import json
+
+from loguru import logger
+
+import coocan
+from coocan import Request, MiniSpider
+
+
+class CSDNDetailSpider(MiniSpider):
+    start_urls = ['http://www.csdn.net']
+    max_requests = 10
+
+    def middleware(self, request: Request):
+        request.headers["Referer"] = "http://www.csdn.net/"
+
+    def parse(self, response):
+        api = "https://blog.csdn.net/community/home-api/v1/get-business-list"
+        params = {
+            "page": "1",
+            "size": "20",
+            "businessType": "lately",
+            "noMore": "false",
+            "username": "markadc"
+        }
+        yield Request(api, self.parse_page, params=params, cb_kwargs={"api": api, "params": params})
+
+    def parse_page(self, response, api, params):
+        current_page = params["page"]
+        data = json.loads(response.text)
+        some = data["data"]["list"]
+
+        if not some:
+            logger.warning("没有第 {} 页".format(current_page))
+            return
+
+        for one in some:
+            date = one["formatTime"]
+            name = one["title"]
+            detail_url = one["url"]
+            logger.info(
+                """
+                {} 
+                {} 
+                {}
+                """.format(date, name, detail_url)
+            )
+            yield coocan.Request(detail_url, self.parse_detail, cb_kwargs={"title": name})
+
+        logger.info("第 {} 页抓取成功".format(params["page"]))
+
+        # 抓取下一页
+        next_page = int(current_page) + 1
+        params["page"] = str(next_page)
+        yield Request(api, self.parse_page, params=params, cb_kwargs={"api": api, "params": params})
+
+    def parse_detail(self, response, title):
+        logger.success("{}  已访问 {}".format(response.status_code, title))
+
+
+if __name__ == '__main__':
+    s = CSDNDetailSpider()
+    s.go()
+```

{coocan-0.4.6 → coocan-0.4.7}/coocan.egg-info/SOURCES.txt

@@ -1,3 +1,4 @@
+README.md
 setup.py
 coocan/__init__.py
 coocan/gen.py

{coocan-0.4.6 → coocan-0.4.7}/setup.py

@@ -1,13 +1,20 @@
 from setuptools import setup, find_packages
 
+with open("README.md", "r", encoding="utf-8") as f:
+    long_description = f.read()
+
 setup(
     name="coocan",
-    version="0.4.6",
+    version="0.4.7",
     author="wauo",
     author_email="markadc@126.com",
     description="Air Spider Framework",
     packages=find_packages(),
     python_requires=">=3.10",
+
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+
     install_requires=[
         'click>=8.0.0', 'httpx', 'loguru'
     ],

coocan-0.4.6/PKG-INFO

@@ -1,7 +0,0 @@
-Metadata-Version: 2.1
-Name: coocan
-Version: 0.4.6
-Summary: Air Spider Framework
-Author: wauo
-Author-email: markadc@126.com
-Requires-Python: >=3.10

coocan-0.4.6/coocan.egg-info/PKG-INFO

@@ -1,7 +0,0 @@
-Metadata-Version: 2.1
-Name: coocan
-Version: 0.4.6
-Summary: Air Spider Framework
-Author: wauo
-Author-email: markadc@126.com
-Requires-Python: >=3.10