orbitkit 0.8.33__tar.gz → 0.8.34__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {orbitkit-0.8.33/orbitkit.egg-info → orbitkit-0.8.34}/PKG-INFO +1 -1
- orbitkit-0.8.34/orbitkit/VERSION +1 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_extractor_netmind_v3.py +0 -2
- {orbitkit-0.8.33 → orbitkit-0.8.34/orbitkit.egg-info}/PKG-INFO +1 -1
- orbitkit-0.8.33/orbitkit/VERSION +0 -1
- {orbitkit-0.8.33 → orbitkit-0.8.34}/LICENSE +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/MANIFEST.in +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/README.md +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/airflow_handler/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/airflow_handler/data_preprocessing.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/airflow_handler/file_flow_entry_process.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/airflow_handler/file_flow_exit_process.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/airflow_handler/file_handler.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/airflow_handler/file_handler_v2.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/audio_transcoder/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/audio_transcoder/netmind_extract_v1.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/constant/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/constant/report_schema.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/id_srv/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/id_srv/id_gen.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/id_srv/id_perm_like.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/lark_send/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/lark_send/lark.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/llm_tools/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/llm_tools/quick_rag_chat.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/orbit_type/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/orbit_type/doc_4_compile_rule.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/orbit_type/orbit_type_simple.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/orbit_type/tools.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_embedding/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_embedding/pdf_txt_embedding.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_embedding/pdf_txt_embedding_v2.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/a_stock_extractor_v1.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/exceptions.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_block_extractor_base.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_block_extractor_v1.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_block_extractor_v2.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_extractor_azure.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_extractor_minerU_v1.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_extractor_netmind_v1.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_extractor_netmind_v2.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor/pdf_extractor_orbit.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor_simple/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor_simple/base.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor_simple/cloud_provider.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor_simple/core.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor_simple/exceptions.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor_simple/extractors.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_extractor_simple/utils.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_writer/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/pdf_writer/pdf_writer_simple.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/__init__.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/common.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/customize_regix_manager.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/secret_manager.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_aliyun.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_aliyun_oss_simple.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_aws.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_aws_s3_wrapper.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_date.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_html.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_kafka.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_md5.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_selenium.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_simple_timer.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_str.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_type_mapping.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit/util/util_url.py +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit.egg-info/SOURCES.txt +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit.egg-info/dependency_links.txt +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit.egg-info/not-zip-safe +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit.egg-info/requires.txt +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/orbitkit.egg-info/top_level.txt +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/setup.cfg +0 -0
- {orbitkit-0.8.33 → orbitkit-0.8.34}/setup.py +0 -0
|
@@ -0,0 +1 @@
|
|
|
1
|
+
0.8.34
|
|
@@ -13,7 +13,6 @@ from orbitkit.util import s3_split_path, S3Util, get_from_dict_or_env, ExtenCons
|
|
|
13
13
|
get_content_type_4_filename
|
|
14
14
|
from typing import Optional
|
|
15
15
|
import urllib3
|
|
16
|
-
from retry import retry
|
|
17
16
|
import fitz # PyMuPDF
|
|
18
17
|
import os
|
|
19
18
|
from tqdm import tqdm
|
|
@@ -158,7 +157,6 @@ class PdfExtractorNetmindExtract:
|
|
|
158
157
|
},
|
|
159
158
|
ExpiresIn=604800)
|
|
160
159
|
|
|
161
|
-
@retry(tries=2, delay=4)
|
|
162
160
|
def get_netmind_response(self, presigned_url):
|
|
163
161
|
start = time.time()
|
|
164
162
|
files = {"url": (None, presigned_url)}
|
orbitkit-0.8.33/orbitkit/VERSION
DELETED
|
@@ -1 +0,0 @@
|
|
|
1
|
-
0.8.33
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|