nber-cli 0.1.0__tar.gz → 0.1.2__tar.gz

{nber_cli-0.1.0 → nber_cli-0.1.2}/PKG-INFO

@@ -1,12 +1,13 @@
 Metadata-Version: 2.4
 Name: nber-cli
-Version: 0.1.0
+Version: 0.1.2
 Summary: A command-line tool to download NBER papers.
 License-File: LICENSE
 Requires-Python: >=3.11
 Requires-Dist: aiohttp
 Requires-Dist: aiohttp-retry
 Requires-Dist: aiosqlite
+Requires-Dist: certifi
 Requires-Dist: fake-useragent
 Requires-Dist: orjson
 Description-Content-Type: text/markdown

{nber_cli-0.1.0 → nber_cli-0.1.2}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "nber-cli"
-version = "0.1.0"
+version = "0.1.2"
 description = "A command-line tool to download NBER papers."
 readme = "README.md"
 requires-python = ">=3.11"
@@ -9,7 +9,8 @@ dependencies = [
     "aiosqlite",
     "orjson",
     "fake_useragent",
-    "aiohttp-retry"
+    "aiohttp-retry",
+    "certifi"
 ]
 
 [project.scripts]
@@ -18,5 +19,3 @@ nber-cli = "nber_cli:main"
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"
-
-

{nber_cli-0.1.0 → nber_cli-0.1.2}/src/nber_cli/downloader.py

@@ -13,10 +13,12 @@ import aiosqlite
 import os
 import time
 import random
-import orjson # 比json更快的JSON库
+import orjson  # 比json更快的JSON库
 from fake_useragent import UserAgent
 from typing import List, Set, Dict, Any
 import logging
+import ssl
+import certifi
 from aiohttp_retry import RetryClient, ExponentialRetry
 import functools
 import concurrent.futures
@@ -123,23 +125,28 @@ async def update_paper_state(paper_id: str, status: str):
 
 async def download_paper(paper_id: str, save_path: str):
     """下载单个NBER论文"""
-    if await get_paper_state(paper_id) == 'ok':
-        logger.info(f"Skipping {paper_id}, already downloaded.")
-        return
-
-    url = f"https://www.nber.org/papers/{paper_id}.pdf"
     filepath = os.path.join(save_path, f"{paper_id}.pdf")
 
     # 确保保存路径存在
     os.makedirs(save_path, exist_ok=True)
 
+    state = await get_paper_state(paper_id)
+    if state == 'ok' and os.path.exists(filepath):
+        logger.info(f"Skipping {paper_id}, already downloaded.")
+        return
+    if state == 'ok' and not os.path.exists(filepath):
+        logger.info(f"{paper_id} marked as downloaded but file missing, re-downloading.")
+
+    url = f"https://www.nber.org/papers/{paper_id}.pdf"
+
     ua = UserAgent()
     headers = {'User-Agent': ua.random}
     retry_options = ExponentialRetry(attempts=MAX_RETRIES)
+    ssl_context = ssl.create_default_context(cafile=certifi.where())
 
     try:
         async with RetryClient(retry_options=retry_options, headers=headers) as session:
-            async with session.get(url, timeout=30) as response:
+            async with session.get(url, timeout=30, ssl=ssl_context) as response:
                 if response.status == 200:
                     content = await response.read()
                     with open(filepath, 'wb') as f:

{nber_cli-0.1.0 → nber_cli-0.1.2}/uv.lock

@@ -124,6 +124,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/77/06/bb80f5f86020c4551da315d78b3ab75e8228f89f0162f2c3a819e407941a/attrs-25.3.0-py3-none-any.whl", hash = "sha256:427318ce031701fea540783410126f03899a97ffc6f61596ad581ac2e40e3bc3", size = 63815, upload-time = "2025-03-13T11:10:21.14Z" },
 ]
 
+[[package]]
+name = "certifi"
+version = "2025.6.15"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/73/f7/f14b46d4bcd21092d7d3ccef689615220d8a08fb25e564b65d20738e672e/certifi-2025.6.15.tar.gz", hash = "sha256:d747aa5a8b9bbbb1bb8c22bb13e22bd1f18e9796defa16bab421f7f7a317323b", size = 158753, upload-time = "2025-06-15T02:45:51.329Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/84/ae/320161bd181fc06471eed047ecce67b693fd7515b16d495d8932db763426/certifi-2025.6.15-py3-none-any.whl", hash = "sha256:2e0c7ce7cb5d8f8634ca55d2ba7e6ec2689a2fd6537d8dec1296a477a4910057", size = 157650, upload-time = "2025-06-15T02:45:49.977Z" },
+]
+
 [[package]]
 name = "fake-useragent"
 version = "2.2.0"
@@ -302,12 +311,13 @@ wheels = [
 
 [[package]]
 name = "nber-cli"
-version = "0.1.0"
+version = "0.1.2"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },
     { name = "aiohttp-retry" },
     { name = "aiosqlite" },
+    { name = "certifi" },
     { name = "fake-useragent" },
     { name = "orjson" },
 ]
@@ -317,6 +327,7 @@ requires-dist = [
     { name = "aiohttp" },
     { name = "aiohttp-retry" },
     { name = "aiosqlite" },
+    { name = "certifi" },
     { name = "fake-useragent" },
     { name = "orjson" },
 ]