♻️ Redesigned Boilerplate (#39)

* ♻️ refactor design

* 🗑️ Deprecated selectolax

* ♻️ improved contracts and base design

* ✅ add rocketry serve test

* 🦺 Update AioHttpEngine `cookies` and `proxy` type

* ✅ Add engine test for attrs

* 🎨 Update pre-commit and `pyproject.toml` and `setup.cfg`

* 🎨 Apply format with conf on all project

* 🔧 update config files

* 🚨 fix mypy type errors

* 🎨 improve core adaptor

* ✅ Update tests

* 👷 Update req-dev

* 👷 Update tox.ini

* 🎨 Improved and centralized protos

* ⚡️ Update `_get_cookie` and add a test for non-setuped engine

---------

Co-authored-by: Sadegh Yazdani <[email protected]>

Author: ManiMozaffar

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ repos:
       - id: check-yaml
       - id: check-added-large-files
   - repo: 'https://github.com/psf/black'
-    rev: 23.3.0
+    rev: 23.7.0
     hooks:
       - id: black
   - repo: 'https://github.com/PyCQA/flake8'
@@ -18,3 +18,8 @@ repos:
     rev: v1.4.1
     hooks:
       - id: mypy
+        name: mypy (fastcrawler)
+        files: ^fastcrawler/
+      # - id: mypy
+      #   name: mypy (test)
+      #   files: ^test/

README.md

@@ -1 +1 @@
-# fastcrawler
+# fastcrawler

docs_src/initilizing_project/sample1/main.py

@@ -2,5 +2,5 @@
 from fastcrawler import FastCrawler
 
 app = FastCrawler(
-    crawlers=wiki_spider
+    crawlers=wiki_spider,
 )

docs_src/initilizing_project/sample1/wikipedia.py

@@ -2,7 +2,7 @@
 
 
 from fastcrawler import BaseModel, Crawler, CSSField, Spider, XPATHField
-from fastcrawler.engine import AioHTTP
+from fastcrawler.engine import AioHttpEngine
 
 
 class PageResolver(BaseModel):
@@ -16,21 +16,24 @@ class ArticleData(BaseModel):
 
 
 class WikiBaseSpider(Spider):
-    engine = AioHTTP
+    engine = AioHttpEngine
     concurrency = 100
 
 
 class WikiArticleFinder(WikiBaseSpider):
     data_model = PageResolver
     req_count = 1_000_000
-    start_url = ["https://meta.wikimedia.org/wiki/List_of_Wikipedias", ]
+    start_url = [
+        "https://meta.wikimedia.org/wiki/List_of_Wikipedias",
+    ]
 
 
 class WikiArticleRetirever(WikiBaseSpider):
     data_model = ArticleData
     req_count = 1_000_000
 
-    async def save_data(self, data: ArticleData): ...  # save parsed data to database
+    async def save_data(self, data: ArticleData):
+        ...  # save parsed data to database
 
 
 wiki_spider = Crawler(WikiArticleFinder >> WikiArticleRetirever)

fastcrawler/__init__.py

@@ -1,5 +1,7 @@
 from .core import Crawler, FastCrawler, Spider
-from .parsers import BaseModel, CSSField, XPATHField, RegexField
+from .engine import AioHttpEngine
+from .parsers import BaseModel, CSSField, RegexField, XPATHField
+from .schedule import RocketryApplication, RocketryController
 from .utils import Depends
 
 __all__ = [
@@ -10,5 +12,8 @@
     "Depends",
     "Spider",
     "Crawler",
-    "FastCrawler"
+    "FastCrawler",
+    "RocketryApplication",
+    "RocketryController",
+    "AioHttpEngine",
 ]

fastcrawler/core/__init__.py

@@ -5,5 +5,5 @@
 __all__ = [
     "Crawler",
     "Spider",
-    "FastCrawler"
+    "FastCrawler",
 ]

fastcrawler/core/registery.py

@@ -9,6 +9,7 @@ class CrawlerMeta(type):
 
     DONT TOUCH THIS CLASS UNLESS YOU KNOW WHAT YOU ARE DOING.
     """
+
     def __init__(cls, name, bases, dct):
         super().__init__(name, bases, dct)
         cls._instances = {}

fastcrawler/core/spider.py

@@ -1,11 +1,25 @@
 from typing import List
 
 
-class SpiderMetaClass(type):
+class Spider:
+    """
+    Spider class to create the actual spider interface
+        so that configuration of each spider can be given
+        as class properties from the inheritanced class from spider
+
+    instances property hold the instances that were set by metaclass
+    that is connected to current spider class
+    """
+
+    instances: List["Spider"]
+
+    def __init__(self):
+        ...
+
     def __rshift__(self, other: "Spider") -> "Spider":
         """
         leveraged RSHIFT method for magic in flow >>
-        objA >> objB >> objC >> objD
+        clsA >> clsB >> clsC >> clsD
 
         Must be used as metaclass to inject behaviour to subclass
 
@@ -17,15 +31,3 @@ def __rshift__(self, other: "Spider") -> "Spider":
         self.instances.append(other)
         setattr(other, "instances", self.instances)
         return other
-
-
-class Spider(metaclass=SpiderMetaClass):
-    """
-    Spider class to create the actual spider interface
-        so that configuration of each spider can be given
-        as class properties from the inheritanced class from spider
-
-    instances property hold the instances that were set by metaclass
-    that is connected to current spider class
-    """
-    instances: List["Spider"]

fastcrawler/engine/__init__.py

@@ -1,8 +1,8 @@
-from .aio import AioHTTP
-from .base import ProxySetting, SetCookieParam
+from .aio import AioHttpEngine
+from .contracts import ProxySetting, SetCookieParam
 
 __all__ = [
     "ProxySetting",
     "SetCookieParam",
-    "AioHTTP",
+    "AioHttpEngine",
 ]

fastcrawler/engine/aio.py

@@ -1,13 +1,15 @@
 import asyncio
+from typing import Any
 
 import pydantic
 from aiohttp import BasicAuth, ClientSession, TCPConnector
+from aiohttp.client import ClientResponse
 from aiohttp.cookiejar import Morsel
 
-from fastcrawler.engine.base import ProxySetting, SetCookieParam
+from fastcrawler.engine.contracts import ProxySetting, Response, SetCookieParam
 
 
-class AioHTTP:
+class AioHttpEngine:
     def __init__(
         self,
         cookies: list[SetCookieParam] | None = None,
@@ -17,9 +19,9 @@ def __init__(
         connection_limit: int = 100,
     ):
         """Initialize a new engine instance with given cookie, header, useragent, and proxy"""
-        self.session = None
+        self.session: None | ClientSession = None
         self._cookies = (
-            [(cookie.name, self.get_morsel_cookie(cookie)) for cookie in cookies]
+            [(cookie.name, self._get_morsel_cookie(cookie)) for cookie in cookies]
             if cookies is not None
             else None
         )
@@ -30,29 +32,39 @@ def __init__(
 
         self._connector = TCPConnector(limit_per_host=connection_limit)
 
-        self._proxy = {}
+        self._proxy: dict[Any, Any] = {}
+        self.proxy_dct = proxy
         if proxy:
             proxy_url = f"{proxy.protocol}{proxy.server}:{proxy.port}"
             self._proxy["proxy"] = proxy_url
             if proxy.username and proxy.password:
-                auth = BasicAuth(login=proxy.username, password=proxy.password)
-                self._proxy["proxy_auth"] = auth
+                self._proxy["proxy_auth"] = BasicAuth(
+                    login=proxy.username, password=proxy.password
+                )
 
     @property
-    def cookies(self):
-        return self._cookies
+    def cookies(self) -> list[SetCookieParam] | None:
+        """Return cookies"""
+        cookies = None
+        if self._cookies is not None:
+            cookies = [self._get_cookie(cookie) for _, cookie in self._cookies]
+
+        return cookies
 
     @property
-    def headers(self):
+    def headers(self) -> dict:
+        """Return headers"""
         return self._headers
 
     @property
-    def proxy(self):
-        return self._proxy
+    def proxy(self) -> ProxySetting | None:
+        """Return proxy setting"""
+        return self.proxy_dct
 
-    def get_morsel_cookie(self, cookie: SetCookieParam) -> Morsel:
+    @staticmethod
+    def _get_morsel_cookie(cookie: SetCookieParam) -> Morsel:
         """Converts a SetCookieParam object to an Morsel object."""
-        morsel_obj = Morsel()
+        morsel_obj: Morsel = Morsel()
         morsel_obj.set(cookie.name, cookie.value, cookie.value)
         morsel_obj.update(
             dict(
@@ -66,6 +78,21 @@ def get_morsel_cookie(self, cookie: SetCookieParam) -> Morsel:
         )
         return morsel_obj
 
+    @staticmethod
+    def _get_cookie(cookie: Morsel) -> SetCookieParam:
+        """convert Morsel object to SetCookieParam object"""
+        cookie_params = {
+            "name": cookie.key,
+            "value": cookie.value,
+            "domain": cookie.get("domain"),
+            "path": cookie.get("path"),
+            "expires": cookie.get("expires"),
+            "httpOnly": cookie.get("httponly"),
+            "secure": cookie.get("secure"),
+            "sameSite": cookie.get("samesite"),
+        }
+        return SetCookieParam(**cookie_params)
+
     async def __aenter__(self):
         """Async context manager support for engine -> ENTER"""
         await self.setup()
@@ -79,46 +106,59 @@ async def setup(self, **kwargs) -> None:
         """Set-up up the engine for crawling purpose."""
         self.session = ClientSession(
             connector=self._connector,
-            cookies=self.cookies,
+            cookies=self._cookies,
             headers=self.headers,
             trust_env=True,
             **kwargs,
         )
 
     async def teardown(self) -> None:
         """Cleans up the engine."""
-        await self.session.close()
+        if self.session:
+            await self.session.close()
 
-    async def base(self, url: pydantic.AnyUrl, method: str, data: dict, **kwargs) -> str:
+    async def base(
+        self, url: pydantic.AnyUrl, method: str, data: dict | None, **kwargs
+    ) -> Response | None:
         """Base Method for protocol to retrieve a list of URL."""
-
-        async with self.session.request(
-            method, url, data=data, headers=self.headers, **self.proxy, **kwargs
-        ) as response:
-            return await response.text()
-
-    async def get(self, urls: list[pydantic.AnyUrl], **kwargs) -> list[str] | str:
+        if self.session:
+            async with self.session.request(
+                method, str(url), data=data, headers=self.headers, **self._proxy, **kwargs
+            ) as response:
+                return await self.translate_to_response(response)
+        return None
+
+    async def get(self, urls: list[pydantic.AnyUrl], **kwargs) -> list[Response]:
         """GET HTTP Method for protocol to retrieve a list of URL."""
         tasks = [self.base(url, "GET", None, **kwargs) for url in urls]
         return await asyncio.gather(*tasks)
 
     async def post(
         self, urls: list[pydantic.AnyUrl], datas: list[dict], **kwargs
-    ) -> list[str] | str:
+    ) -> list[Response]:
         """POST HTTP Method for protocol to crawl a list of URL."""
         tasks = [self.base(url, "POST", data=data, **kwargs) for url, data in zip(urls, datas)]
         return await asyncio.gather(*tasks)
 
     async def put(
         self, urls: list[pydantic.AnyUrl], datas: list[dict], **kwargs
-    ) -> list[str] | str:
+    ) -> list[Response]:
         """PUT HTTP Method for protocol to crawl a list of URL."""
-        tasks = [self.base(url, "PUT", data=data) for url, data in zip(urls, datas)]
+        tasks = [self.base(url, "PUT", data=data, **kwargs) for url, data in zip(urls, datas)]
         return await asyncio.gather(*tasks)
 
     async def delete(
         self, urls: list[pydantic.AnyUrl], datas: list[dict], **kwargs
-    ) -> list[str] | str:
+    ) -> list[Response]:
         """DELETE HTTP Method for protocol to crawl a list of URL."""
         tasks = [self.base(url, "DELETE", data=data, **kwargs) for url, data in zip(urls, datas)]
         return await asyncio.gather(*tasks)
+
+    async def translate_to_response(self, response_obj: ClientResponse) -> Response:
+        """Translate aiohttp response object to Response object"""
+        return Response(
+            text=await response_obj.text(),
+            status_code=response_obj.status,
+            headers=response_obj.headers,
+            cookie=response_obj.cookies,
+        )

fastcrawler/engine/constants.py

@@ -7,15 +7,15 @@
 
 
 class SetCookieParam(pydantic.BaseModel):
-    name: str
-    value: str
+    name: str = ""
+    value: str = ""
     url: str | None = None
     domain: str = ""
-    path: str | None = None
-    expires: float | None = None
-    httpOnly: bool | None = None
-    secure: bool | None = None
-    sameSite: Literal["Lax", "None", "Strict"] | None = None
+    path: str = ""
+    expires: str = ""
+    httpOnly: str = ""
+    secure: str = ""
+    sameSite: str | Literal["Lax", "None", "Strict"] = ""
 
 
 class ProxySetting(pydantic.BaseModel):
@@ -26,6 +26,13 @@ class ProxySetting(pydantic.BaseModel):
     password: str | None = None
 
 
+class Response(pydantic.BaseModel):
+    text: str | None = None
+    status_code: int | None = None
+    headers: dict | None = None
+    cookie: dict | None = None
+
+
 class EngineProto(Protocol):
     def __init__(
         self,
@@ -34,7 +41,7 @@ def __init__(
         useragent: str | None,
         proxy: ProxySetting | None,
     ):
-        """Initialize a new engine instance with given cookie(s), header(s), useragent, and proxy"""
+        "Initialize a new engine instance with given cookie(s), header(s), useragent, and proxy"
 
     async def __aenter__(self):
         """Async context manager support for engine -> ENTER"""
@@ -62,3 +69,6 @@ async def put(self, urls: list[pydantic.AnyUrl], datas: list[dict]) -> str:
 
     async def delete(self, urls: list[pydantic.AnyUrl], datas: list[dict]) -> str:
         """DELETE HTTP Method for protocol to crawl a list of URL."""
+
+    async def translate_to_response(self, response_obj: type) -> Response:
+        """Translate the response object to a Response object"""