aio-scrapy 2.0.7__tar.gz → 2.0.9__tar.gz

{aio-scrapy-2.0.7/aio_scrapy.egg-info → aio-scrapy-2.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: aio-scrapy
-Version: 2.0.7
+Version: 2.0.9
 Summary: A high-level Web Crawling and Web Scraping framework based on Asyncio
 Home-page: https://github.com/conlin-huang/aio-scrapy.git
 Author: conlin
@@ -18,17 +18,47 @@ Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: aiohttp
+Requires-Dist: ujson
+Requires-Dist: w3lib>=1.17.0
+Requires-Dist: parsel>=1.5.0
+Requires-Dist: PyDispatcher>=2.0.5
+Requires-Dist: zope.interface>=5.1.0
+Requires-Dist: redis>=4.3.1
+Requires-Dist: aiomultiprocess>=0.9.0
+Requires-Dist: loguru>=0.7.0
 Provides-Extra: all
+Requires-Dist: aiomysql>=0.1.1; extra == "all"
+Requires-Dist: httpx[http2]>=0.23.0; extra == "all"
+Requires-Dist: aio-pika>=8.1.1; extra == "all"
+Requires-Dist: cryptography; extra == "all"
+Requires-Dist: motor>=3.1.1; extra == "all"
+Requires-Dist: pyhttpx>=2.10.1; extra == "all"
+Requires-Dist: asyncpg>=0.27.0; extra == "all"
+Requires-Dist: XlsxWriter>=3.1.2; extra == "all"
+Requires-Dist: pillow>=9.4.0; extra == "all"
+Requires-Dist: requests>=2.28.2; extra == "all"
 Provides-Extra: aiomysql
+Requires-Dist: aiomysql>=0.1.1; extra == "aiomysql"
+Requires-Dist: cryptography; extra == "aiomysql"
 Provides-Extra: httpx
+Requires-Dist: httpx[http2]>=0.23.0; extra == "httpx"
 Provides-Extra: aio-pika
+Requires-Dist: aio-pika>=8.1.1; extra == "aio-pika"
 Provides-Extra: mongo
+Requires-Dist: motor>=3.1.1; extra == "mongo"
 Provides-Extra: playwright
+Requires-Dist: playwright>=1.31.1; extra == "playwright"
 Provides-Extra: pyhttpx
+Requires-Dist: pyhttpx>=2.10.4; extra == "pyhttpx"
 Provides-Extra: requests
+Requires-Dist: requests>=2.28.2; extra == "requests"
 Provides-Extra: pg
+Requires-Dist: asyncpg>=0.27.0; extra == "pg"
 Provides-Extra: execl
-License-File: LICENSE
+Requires-Dist: XlsxWriter>=3.1.2; extra == "execl"
+Requires-Dist: pillow>=9.4.0; extra == "execl"
 
 <!--
 ![aio-scrapy](./doc/images/aio-scrapy.png)

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9/aio_scrapy.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: aio-scrapy
-Version: 2.0.7
+Version: 2.0.9
 Summary: A high-level Web Crawling and Web Scraping framework based on Asyncio
 Home-page: https://github.com/conlin-huang/aio-scrapy.git
 Author: conlin
@@ -18,17 +18,47 @@ Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: aiohttp
+Requires-Dist: ujson
+Requires-Dist: w3lib>=1.17.0
+Requires-Dist: parsel>=1.5.0
+Requires-Dist: PyDispatcher>=2.0.5
+Requires-Dist: zope.interface>=5.1.0
+Requires-Dist: redis>=4.3.1
+Requires-Dist: aiomultiprocess>=0.9.0
+Requires-Dist: loguru>=0.7.0
 Provides-Extra: all
+Requires-Dist: aiomysql>=0.1.1; extra == "all"
+Requires-Dist: httpx[http2]>=0.23.0; extra == "all"
+Requires-Dist: aio-pika>=8.1.1; extra == "all"
+Requires-Dist: cryptography; extra == "all"
+Requires-Dist: motor>=3.1.1; extra == "all"
+Requires-Dist: pyhttpx>=2.10.1; extra == "all"
+Requires-Dist: asyncpg>=0.27.0; extra == "all"
+Requires-Dist: XlsxWriter>=3.1.2; extra == "all"
+Requires-Dist: pillow>=9.4.0; extra == "all"
+Requires-Dist: requests>=2.28.2; extra == "all"
 Provides-Extra: aiomysql
+Requires-Dist: aiomysql>=0.1.1; extra == "aiomysql"
+Requires-Dist: cryptography; extra == "aiomysql"
 Provides-Extra: httpx
+Requires-Dist: httpx[http2]>=0.23.0; extra == "httpx"
 Provides-Extra: aio-pika
+Requires-Dist: aio-pika>=8.1.1; extra == "aio-pika"
 Provides-Extra: mongo
+Requires-Dist: motor>=3.1.1; extra == "mongo"
 Provides-Extra: playwright
+Requires-Dist: playwright>=1.31.1; extra == "playwright"
 Provides-Extra: pyhttpx
+Requires-Dist: pyhttpx>=2.10.4; extra == "pyhttpx"
 Provides-Extra: requests
+Requires-Dist: requests>=2.28.2; extra == "requests"
 Provides-Extra: pg
+Requires-Dist: asyncpg>=0.27.0; extra == "pg"
 Provides-Extra: execl
-License-File: LICENSE
+Requires-Dist: XlsxWriter>=3.1.2; extra == "execl"
+Requires-Dist: pillow>=9.4.0; extra == "execl"
 
 <!--
 ![aio-scrapy](./doc/images/aio-scrapy.png)

aio-scrapy-2.0.9/aioscrapy/VERSION

@@ -0,0 +1 @@
+2.0.9

aio-scrapy-2.0.9/aioscrapy/dupefilters/__init__.py

@@ -0,0 +1,39 @@
+from abc import ABCMeta, abstractmethod
+
+from aioscrapy import Request, Spider
+from aioscrapy.utils.log import logger
+
+
+class DupeFilterBase(metaclass=ABCMeta):
+    """Request Fingerprint duplicates filter"""
+
+    @classmethod
+    @abstractmethod
+    def from_crawler(cls, crawler: "aioscrapy.crawler.Crawler"):
+        """ Get Instance of RFPDupeFilter from crawler """
+
+    @abstractmethod
+    async def request_seen(self, request: Request) -> bool:
+        """ Check whether fingerprint of request exists """
+
+    @abstractmethod
+    async def close(self, reason: str = '') -> None:
+        """ Delete data on close """
+
+    def log(self, request: Request, spider: Spider):
+        if self.info:
+            logger.info("Filtered duplicate request: %(request)s" % {
+                'request': request.meta.get('dupefilter_msg') or request
+            })
+        elif self.debug:
+            logger.debug("Filtered duplicate request: %(request)s" % {
+                'request': request.meta.get('dupefilter_msg') or request
+            })
+        elif self.logdupes:
+            msg = ("Filtered duplicate request: %(request)s"
+                   " - no more duplicates will be shown"
+                   " (see DUPEFILTER_DEBUG to show all duplicates)")
+            logger.debug(msg % {'request': request.meta.get('dupefilter_msg') or request})
+            self.logdupes = False
+
+        spider.crawler.stats.inc_value('dupefilter/filtered', spider=spider)

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/dupefilters/disk.py

@@ -1,20 +1,19 @@
 import os
 from typing import Optional, Set
 
-from aioscrapy import Request, Spider
+from aioscrapy import Request
 from aioscrapy.dupefilters import DupeFilterBase
-from aioscrapy.utils.log import logger
-from aioscrapy.utils.request import referer_str
 
 
 class DiskRFPDupeFilter(DupeFilterBase):
     """Request Fingerprint duplicates filter built with Disk storage"""
 
-    def __init__(self, path: Optional[str] = None, debug: bool = False):
+    def __init__(self, path: Optional[str] = None, debug: bool = False, info: bool = False):
         self.file: Optional["File object"] = None
         self.debug = debug
         self.fingerprints: Set = set()
         self.logdupes: bool = True
+        self.info: bool = info
         if path:
             self.file = open(os.path.join(path, 'requests.seen'), 'a+')
             self.file.seek(0)
@@ -23,10 +22,11 @@ class DiskRFPDupeFilter(DupeFilterBase):
     @classmethod
     def from_crawler(cls, crawler: "aioscrapy.crawler.Crawler"):
         debug = crawler.settings.getbool('DUPEFILTER_DEBUG')
+        info = crawler.settings.getbool('DUPEFILTER_INFO')
         path = crawler.settings.get('JOBDIR', './job_dir')
         if path and not os.path.exists(path):
             os.makedirs(path)
-        return cls(path, debug)
+        return cls(path, debug, info)
 
     async def request_seen(self, request: Request) -> bool:
         if request.fingerprint in self.fingerprints:
@@ -40,19 +40,5 @@ class DiskRFPDupeFilter(DupeFilterBase):
         if self.file:
             self.file.close()
 
-    def log(self, request: Request, spider: Spider):
-        if self.debug:
-            logger.debug("Filtered duplicate request: %(request)s (referer: %(referer)s)" % {
-                'request': request, 'referer': referer_str(request)
-            })
-        elif self.logdupes:
-            msg = ("Filtered duplicate request: %(request)s"
-                   " - no more duplicates will be shown"
-                   " (see DUPEFILTER_DEBUG to show all duplicates)")
-            logger.debug(msg % {'request': request})
-            self.logdupes = False
-
-        spider.crawler.stats.inc_value('dupefilter/filtered', spider=spider)
-
 
 RFPDupeFilter = DiskRFPDupeFilter

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/dupefilters/redis.py

@@ -2,8 +2,6 @@ from aioscrapy import Request
 from aioscrapy.db import db_manager
 from aioscrapy.dupefilters import DupeFilterBase
 
-from aioscrapy.utils.log import logger
-
 
 class RedisRFPDupeFilter(DupeFilterBase):
     """Request Fingerprint duplicates filter built with Set of Redis"""
@@ -13,13 +11,15 @@ class RedisRFPDupeFilter(DupeFilterBase):
             server: "redis.asyncio.Redis",
             key: str,
             debug: bool = False,
-            keep_on_close: bool = True
+            keep_on_close: bool = True,
+            info: bool = False,
     ):
         self.server = server
         self.key = key
         self.debug = debug
         self.keep_on_close = keep_on_close
         self.logdupes: bool = True
+        self.info: bool = info
 
     @classmethod
     def from_crawler(cls, crawler: "aioscrapy.crawler.Crawler"):
@@ -28,7 +28,8 @@ class RedisRFPDupeFilter(DupeFilterBase):
         keep_on_close = crawler.settings.getbool("KEEP_DUPEFILTER_DATA_ON_CLOSE", True)
         key = dupefilter_key % {'spider': crawler.spider.name}
         debug = crawler.settings.getbool('DUPEFILTER_DEBUG', False)
-        instance = cls(server, key=key, debug=debug, keep_on_close=keep_on_close)
+        info = crawler.settings.getbool('DUPEFILTER_DEBUG', False)
+        instance = cls(server, key=key, debug=debug, keep_on_close=keep_on_close, info=info)
         return instance
 
     async def request_seen(self, request: Request):
@@ -41,17 +42,6 @@ class RedisRFPDupeFilter(DupeFilterBase):
     async def clear(self):
         await self.server.delete(self.key)
 
-    def log(self, request, spider):
-        if self.debug:
-            logger.debug("Filtered duplicate request: %(request)s" % {'request': request})
-        elif self.logdupes:
-            msg = ("Filtered duplicate request %(request)s"
-                   " - no more duplicates will be shown"
-                   " (see DUPEFILTER_DEBUG to show all duplicates)")
-            logger.debug(msg % {'request': request})
-            self.logdupes = False
-        spider.crawler.stats.inc_value('dupefilter/filtered', spider=spider)
-
 
 class HashMap(object):
     def __init__(self, m, seed):

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/libs/downloader/retry.py

@@ -26,6 +26,13 @@ try:
 except ImportError:
     pass
 
+try:
+    from anyio import EndOfStream
+
+    NEED_RETRY_ERROR += (EndOfStream,)
+except ImportError:
+    pass
+
 try:
     from httpx import HTTPError as HttpxError
 

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/queue/__init__.py

@@ -37,10 +37,10 @@ class AbsQueue(metaclass=ABCMeta):
         obj = request.to_dict(spider=self.spider)
         return self.serializer.dumps(obj)
 
-    def _decode_request(self, encoded_request: Any) -> aioscrapy.Request:
+    async def _decode_request(self, encoded_request: Any) -> aioscrapy.Request:
         """Decode an request previously encoded"""
         obj = self.serializer.loads(encoded_request)
-        return request_from_dict(obj, spider=self.spider)
+        return await request_from_dict(obj, spider=self.spider)
 
     def __len__(self) -> None:
         """Return the length of the queue"""

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/queue/memory.py

@@ -58,7 +58,7 @@ class MemoryQueueBase(AbsQueue):
                 data = self.container.get_nowait()
             except QueueEmpty:
                 break
-            yield self._decode_request(data)
+            yield await self._decode_request(data)
 
     async def clear(self, timeout: int = 0) -> None:
         self.container = self.get_queue(self.max_size)
@@ -93,7 +93,7 @@ class MemoryPriorityQueue(MemoryFifoQueue):
                 score, data = self.container.get_nowait()
             except QueueEmpty:
                 break
-            yield self._decode_request(data)
+            yield await self._decode_request(data)
 
 
 SpiderQueue = MemoryFifoQueue

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/queue/rabbitmq.py

@@ -57,7 +57,7 @@ class RabbitMqPriorityQueue(AbsQueue):
     async def pop(self, count: int = 1) -> Optional[aioscrapy.Request]:
         result = await self.container.get_message(self.key)
         if result:
-            yield self._decode_request(result)
+            yield await self._decode_request(result)
 
     async def clear(self) -> None:
         await self.container.clean_message_queue(self.key)

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/queue/redis.py

@@ -67,7 +67,7 @@ class RedisFifoQueue(RedisQueueBase):
             results = await pipe.execute()
         for result in results:
             if result:
-                yield self._decode_request(result)
+                yield await self._decode_request(result)
 
 
 class RedisPriorityQueue(RedisQueueBase):
@@ -97,7 +97,7 @@ class RedisPriorityQueue(RedisQueueBase):
                 .execute()
             )
         for result in results:
-            yield self._decode_request(result)
+            yield await self._decode_request(result)
 
 
 class RedisLifoQueue(RedisQueueBase):
@@ -124,7 +124,7 @@ class RedisLifoQueue(RedisQueueBase):
             results = await pipe.execute()
         for result in results:
             if result:
-                yield self._decode_request(result)
+                yield await self._decode_request(result)
 
 
 SpiderQueue = RedisFifoQueue

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/spiders/__init__.py

@@ -76,7 +76,7 @@ class Spider(object):
         for url in self.start_urls:
             yield Request(url)
 
-    def request_from_dict(self, d: dict):
+    async def request_from_dict(self, d: dict):
         """集成后重写改方法，将队列中的json根据情况构建成Request对象"""
         pass
 

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/utils/log.py

@@ -7,7 +7,9 @@ from loguru import logger as _logger
 
 from aioscrapy.settings import Settings
 
-_logger.remove(0)
+for _handler in _logger._core.handlers.values():
+    if _handler._name == '<stderr>':
+        _logger.remove(_handler._id)
 
 
 def configure_logging(spider: Type["Spider"], settings: Settings):

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/utils/reqser.py

@@ -11,5 +11,5 @@ def request_to_dict(request: "aioscrapy.Request", spider: Optional["aioscrapy.Sp
     return request.to_dict(spider=spider)
 
 
-def request_from_dict(d: dict, spider: Optional["aioscrapy.Spider"] = None) -> "aioscrapy.Request":
-    return _from_dict(d, spider=spider)
+async def request_from_dict(d: dict, spider: Optional["aioscrapy.Spider"] = None) -> "aioscrapy.Request":
+    return await _from_dict(d, spider=spider)

{aio-scrapy-2.0.7 → aio-scrapy-2.0.9}/aioscrapy/utils/request.py

@@ -39,13 +39,13 @@ def referer_str(request: Request) -> Optional[str]:
     return to_unicode(referrer, errors='replace')
 
 
-def request_from_dict(d: dict, *, spider: Optional[Spider] = None) -> Request:
+async def request_from_dict(d: dict, *, spider: Optional[Spider] = None) -> Request:
     """Create a :class:`~scrapy.Request` object from a dict.
 
     If a spider is given, it will try to resolve the callbacks looking at the
     spider for methods with the same name.
     """
-    d = spider.request_from_dict(d) or d
+    d = await spider.request_from_dict(d) or d
     if isinstance(d, Request):
         return d
 

aio-scrapy-2.0.7/aioscrapy/VERSION

@@ -1 +0,0 @@
-2.0.7

aio-scrapy-2.0.7/aioscrapy/dupefilters/__init__.py

@@ -1,24 +0,0 @@
-from abc import ABCMeta, abstractmethod
-
-from aioscrapy import Request, Spider
-
-
-class DupeFilterBase(metaclass=ABCMeta):
-    """Request Fingerprint duplicates filter"""
-
-    @classmethod
-    @abstractmethod
-    def from_crawler(cls, crawler: "aioscrapy.crawler.Crawler"):
-        """ Get Instance of RFPDupeFilter from crawler """
-
-    @abstractmethod
-    async def request_seen(self, request: Request) -> bool:
-        """ Check whether fingerprint of request exists """
-
-    @abstractmethod
-    async def close(self, reason: str = '') -> None:
-        """ Delete data on close """
-
-    @abstractmethod
-    def log(self, request: Request, spider: Spider) -> None:
-        """ Logs given request """