cobweb-launcher 1.0.7__tar.gz → 1.0.9__tar.gz

{cobweb-launcher-1.0.7/cobweb_launcher.egg-info → cobweb-launcher-1.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cobweb-launcher
-Version: 1.0.7
+Version: 1.0.9
 Summary: spider_hole
 Home-page: https://github.com/Juannie-PP/cobweb
 Author: Juannie-PP

{cobweb-launcher-1.0.7 → cobweb-launcher-1.0.9}/cobweb/base/request.py

@@ -70,3 +70,13 @@ class Request:
             response.raise_for_status()
         return response
 
+    @property
+    def to_dict(self):
+        _dict = self.__dict__.copy()
+        _dict.pop('url')
+        _dict.pop('seed')
+        _dict.pop('check_status_code')
+        _dict.pop('request_setting')
+        return _dict
+
+

{cobweb-launcher-1.0.7 → cobweb-launcher-1.0.9}/cobweb/crawlers/file_crawler.py

@@ -35,20 +35,20 @@ class CrawlerAir(Crawler):
 
                 response = item.download()
 
-                content_length = response.headers.get("content-length") or 0
+                content_length = int(response.headers.get("content-length", 0))
                 content_type = response.headers.get("content-type", "").split(";")[0]
                 if content_type and content_type in setting.FILE_FILTER_CONTENT_TYPE:
                     yield Response(
                         item.seed, response, filter=True, msg=f"response content type is {content_type}",
                         bucket_name=bucket_name, data_size=content_length, **seed_dict
                     )
-                elif position == 1 and min_upload_size >= int(content_length) > 0:
+                elif position == 1 and min_upload_size >= content_length > 0:
                     """过小文件标识返回"""
                     yield Response(
                         item.seed, response, filter=True, msg="file size is too small",
                         bucket_name=bucket_name, data_size=content_length, **seed_dict
                     )
-                elif position == 1 and chunk_size > int(content_length) > min_upload_size:
+                elif position == 1 and chunk_size > content_length > min_upload_size:
                     """小文件直接下载"""
                     for part_data in response.iter_content(chunk_size):
                         content += part_data
@@ -117,20 +117,20 @@ class CrawlerPro(Crawler):
 
                 response = item.download()
 
-                content_length = response.headers.get("content-length") or 0
+                content_length = int(response.headers.get("content-length", 0))
                 content_type = response.headers.get("content-type", "").split(";")[0]
                 if content_type and content_type in setting.FILE_FILTER_CONTENT_TYPE:
                     yield Response(
                         item.seed, response, filter=True, msg=f"response content type is {content_type}",
                         bucket_name=bucket_name, data_size=content_length, **seed_dict
                     )
-                elif position == 1 and min_upload_size >= int(content_length) > 0:
+                elif position == 1 and min_upload_size >= content_length > 0:
                     """过小文件标识返回"""
                     yield Response(
                         item.seed, response, filter=True, msg="file size is too small",
                         bucket_name=bucket_name, data_size=content_length, **seed_dict
                     )
-                elif position == 1 and chunk_size > int(content_length) > min_upload_size:
+                elif position == 1 and chunk_size > content_length > min_upload_size:
                     """小文件直接下载"""
                     for part_data in response.iter_content(chunk_size):
                         content += part_data
@@ -160,15 +160,12 @@ class CrawlerPro(Crawler):
                         content_length += len(content)
                     CrawlerAir.oss_util.merge(key, upload_id)
                     yield Response(item.seed, response, bucket_name=bucket_name, data_size=content_length, **seed_dict)
-                    # data, cols = download_meta(item.seed, bucket_name, data_size=content_length, **seed_dict)
-                    # yield DownloadItem(item.seed, sid=item.seed.sid, cols=cols, data=data)
 
             elif item.seed.params.identifier == "merge":
                 CrawlerAir.oss_util.merge(key, seed_dict["upload_id"])
                 content_length = CrawlerAir.oss_util.head(key).content_length
                 yield Response(item.seed, "merge", bucket_name=bucket_name, data_size=content_length, **seed_dict)
-                # data, cols = download_meta(item.seed, bucket_name, data_size=content_length, **seed_dict)
-                # yield DownloadItem(item.seed, sid=item.seed.sid, cols=cols, data=data)
+
         except OssDBPutPartError:
             yield Seed(seed_dict)
         except OssDBMergeError:

{cobweb-launcher-1.0.7 → cobweb-launcher-1.0.9/cobweb_launcher.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: cobweb-launcher
-Version: 1.0.7
+Version: 1.0.9
 Summary: spider_hole
 Home-page: https://github.com/Juannie-PP/cobweb
 Author: Juannie-PP

{cobweb-launcher-1.0.7 → cobweb-launcher-1.0.9}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
 
 setup(
     name="cobweb-launcher",
-    version="1.0.7",
+    version="1.0.9",
     packages=find_packages(),
     url="https://github.com/Juannie-PP/cobweb",
     license="MIT",