warn-scraper 1.2.167.dev0__py3-none-any.whl → 1.2.169.dev0__py3-none-any.whl

warn/scrapers/nd.py

@@ -0,0 +1,96 @@
+import logging
+import re
+from pathlib import Path
+
+import pdfplumber
+
+from .. import utils
+from ..cache import Cache
+
+__authors__ = ["riordan"]
+__tags__ = ["pdf"]
+__source__ = {
+    "name": "Job Service North Dakota",
+    "url": "https://www.jobsnd.com/documents",
+}
+
+logger = logging.getLogger(__name__)
+
+
+def scrape(
+    data_dir: Path = utils.WARN_DATA_DIR,
+    cache_dir: Path = utils.WARN_CACHE_DIR,
+) -> Path:
+    """
+    Scrape data from North Dakota.
+
+    Keyword arguments:
+    data_dir -- the Path were the result will be saved (default WARN_DATA_DIR)
+    cache_dir -- the Path where results can be cached (default WARN_CACHE_DIR)
+
+    Returns: the Path where the file is written
+    """
+    # Fire up the cache
+    cache = Cache(cache_dir)
+    state_code = "nd"
+
+    # North Dakota publishes a single static PDF covering 2015 to the present.
+    pdf_url = "https://www.jobsnd.com/sites/www/files/documents/jsnd-documents/WARN%20Notices%202015%20to%20present.pdf"
+
+    # Download the PDF and stash the raw file, unedited, in the cache
+    cache_key = f"{state_code}/WARN_Notices_2015_to_present.pdf"
+    pdf_path = cache.download(cache_key, pdf_url)
+
+    # Loop through the PDF pages and pull out the table
+    output_rows: list = []
+    header_written = False
+    with pdfplumber.open(pdf_path) as pdf:
+        for page_index, page in enumerate(pdf.pages):
+            rows = page.extract_table() or []
+
+            for row in rows:
+                # Standardize each cell
+                output_row = [_clean_text(cell) for cell in row]
+
+                # Skip fully empty rows
+                if not any(output_row):
+                    continue
+
+                # The header repeats at the top of the table. Keep it once.
+                if output_row[0] == "Company Name":
+                    if header_written:
+                        logger.debug(
+                            f"Skipping repeated header row on page {page_index + 1}"
+                        )
+                        continue
+                    header_written = True
+
+                output_rows.append(output_row)
+
+    # Write out to CSV
+    data_path = data_dir / f"{state_code}.csv"
+    utils.write_rows_to_csv(data_path, output_rows)
+
+    # Return the path
+    return data_path
+
+
+def _clean_text(text: str) -> str:
+    """
+    Clean up text from a PDF cell.
+
+    Keyword arguments:
+    text -- the text to clean
+
+    Returns: the cleaned text
+    """
+    # Replace None with an empty string
+    if text is None:
+        return ""
+
+    # Collapse newlines and standardize whitespace
+    return re.sub(r"\s+", " ", text).strip()
+
+
+if __name__ == "__main__":
+    scrape()

warn/scrapers/tx.py

@@ -44,6 +44,7 @@ def scrape(
     session = requests.Session()
 
     page = session.get(url)
+    logger.debug(f"Page retrieval with response code {page.status_code}")
 
     #    page = utils.get_url(
     #        url,

{warn_scraper-1.2.167.dev0.dist-info → warn_scraper-1.2.169.dev0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warn-scraper
-Version: 1.2.167.dev0
+Version: 1.2.169.dev0
 Summary: Command-line interface for downloading WARN Act notices of qualified plant closings and mass layoffs from state government websites
 Author-email: Big Local News <biglocalnews@stanford.edu>
 License-Expression: Apache-2.0

{warn_scraper-1.2.167.dev0.dist-info → warn_scraper-1.2.169.dev0.dist-info}/RECORD

@@ -36,6 +36,7 @@ warn/scrapers/mi.py,sha256=Ppyawp4nbzSBODuzDKeqnO9_9do5MFwK4Y_f3uc6blE,5846
 warn/scrapers/mo.py,sha256=wnnwQAiVPwuheMqptMXZpyQdiKNghhKwTO-Bnh9oXoU,3492
 warn/scrapers/ms.py,sha256=BZZoMw3TNtwzBeBsqKLsPznBcDjPaO49I5-yBU0e9AI,5502
 warn/scrapers/mt.py,sha256=t2MP4OCcuCEnrnvNgOu289P0eekZq4XaCK65qzgZX88,2457
+warn/scrapers/nd.py,sha256=x-mLrysn-Ns3tXg6MmjUYZ-4T0x6YUix_fuIldO5Dk0,2657
 warn/scrapers/ne.py,sha256=JawuGJ3tCKvMd-N-p03gnltB4rol4QUJshMk2oyMPO4,4143
 warn/scrapers/nj.py,sha256=nwbMbeQuUJbYRVoyUyKZBmNqvqsXu3Habt-10r8DvZE,2230
 warn/scrapers/nm.py,sha256=55kDh65uOc-uMO8wuxPHhHN4Aw8Di2Fx66JBds8f2Io,3694
@@ -48,17 +49,17 @@ warn/scrapers/ri.py,sha256=EUyLy59eNiYHqiJR8C0YcJrZtp09KyVc45AFD0_Uc0U,4497
 warn/scrapers/sc.py,sha256=p3kscSNSW9C8C5QaSUbCAo6XibgB7G2iH6zaMH7Mnsc,4819
 warn/scrapers/sd.py,sha256=_4R19Ybzsyx1PvcWV3_laJmJ3etrwVGfhNEQm6njwoA,1904
 warn/scrapers/tn.py,sha256=i1H7c09Ea3CDrTXqqRMLBMPT_34QtGA0-x7T8rm_j5Q,2945
-warn/scrapers/tx.py,sha256=y_pRNuTzaQBkHpRKJXA5Fw8ZsjyPJIVElcwGinlf9wk,5594
+warn/scrapers/tx.py,sha256=b9CWn9erFbYFvTacHUy7x-2YfjSuf_VGyt2bUlwq0c8,5668
 warn/scrapers/ut.py,sha256=iUh38YIjbvv5MyyKacsiZNe8KjfdBeDaOf-qMQEF_kc,2245
 warn/scrapers/va.py,sha256=7Nle7qL0VNPiE653XyaP9HQqSfuJFDRr2kEkjOqLvFM,11269
 warn/scrapers/vt.py,sha256=d-bo4WK2hkrk4BhCCmLpEovcoZltlvdIUB6O0uaMx5A,1186
 warn/scrapers/wa.py,sha256=UXdVtHZo_a-XfoiyOooTRfTb9W3PErSZdKca6SRORgs,4282
 warn/scrapers/wi.py,sha256=ClEzXkwZbop0W4fkQgsb5oHAPUrb4luUPGV-jOKwkcg,4855
-warn_scraper-1.2.167.dev0.dist-info/licenses/LICENSE,sha256=ZV-QHyqPwyMuwuj0lI05JeSjV1NyzVEk8Yeu7FPtYS0,585
-warn_scraper-1.2.167.dev0.dist-info/METADATA,sha256=o8cXc8EYMBQsINkZuOBP3Htq8b0ivMlcghMBvDULdsM,1780
-warn_scraper-1.2.167.dev0.dist-info/WHEEL,sha256=K260EYznzXsJYBQGqmI8VTxEdiZYNvDZwW9cBh9-_MA,91
-warn_scraper-1.2.167.dev0.dist-info/entry_points.txt,sha256=poh_oSweObGlBSs1_2qZmnTodlOYD0KfO7-h7W2UQIw,47
-warn_scraper-1.2.167.dev0.dist-info/scm_file_list.json,sha256=SBROd7oEfcspIMl6v7yfGzQd2rkWxybkiIXopuTQVL0,4120
-warn_scraper-1.2.167.dev0.dist-info/scm_version.json,sha256=nJW_1cgs89YVm56svBNN1TWCOn0itYdI0qFA45a9Guw,161
-warn_scraper-1.2.167.dev0.dist-info/top_level.txt,sha256=dZfms6N3kqVXufiPOo7YqOrAcUtYfNH_oyGvYUk9FB4,5
-warn_scraper-1.2.167.dev0.dist-info/RECORD,,
+warn_scraper-1.2.169.dev0.dist-info/licenses/LICENSE,sha256=ZV-QHyqPwyMuwuj0lI05JeSjV1NyzVEk8Yeu7FPtYS0,585
+warn_scraper-1.2.169.dev0.dist-info/METADATA,sha256=idfAf3i-wQj6UbjYHXsG73B3pU8lvD4soFhnBis-e5c,1780
+warn_scraper-1.2.169.dev0.dist-info/WHEEL,sha256=K260EYznzXsJYBQGqmI8VTxEdiZYNvDZwW9cBh9-_MA,91
+warn_scraper-1.2.169.dev0.dist-info/entry_points.txt,sha256=poh_oSweObGlBSs1_2qZmnTodlOYD0KfO7-h7W2UQIw,47
+warn_scraper-1.2.169.dev0.dist-info/scm_file_list.json,sha256=PsUNADDLfiY6WCIaKYrGF-hSOzV6HMBxtHeJPnHAOAo,4147
+warn_scraper-1.2.169.dev0.dist-info/scm_version.json,sha256=4YY6UpShLyl1mHlnjJR2Fi1BirY30YZrm1c8Wg1OkHA,161
+warn_scraper-1.2.169.dev0.dist-info/top_level.txt,sha256=dZfms6N3kqVXufiPOo7YqOrAcUtYfNH_oyGvYUk9FB4,5
+warn_scraper-1.2.169.dev0.dist-info/RECORD,,

{warn_scraper-1.2.167.dev0.dist-info → warn_scraper-1.2.169.dev0.dist-info}/scm_file_list.json

@@ -77,6 +77,7 @@
     "warn/scrapers/al.py",
     "warn/scrapers/fl.py",
     "warn/scrapers/nj.py",
+    "warn/scrapers/nd.py",
     "warn/scrapers/mi.py",
     "warn/scrapers/vt.py",
     "warn/scrapers/mt.py",

warn_scraper-1.2.169.dev0.dist-info/scm_version.json

@@ -0,0 +1,8 @@
+{
+  "tag": "1.2.168",
+  "distance": 0,
+  "node": "gf7b3dd26af1f3ad700762504bd7c5c0d23979507",
+  "dirty": true,
+  "branch": "HEAD",
+  "node_date": "2026-07-14"
+}

warn_scraper-1.2.167.dev0.dist-info/scm_version.json

@@ -1,8 +0,0 @@
-{
-  "tag": "1.2.166",
-  "distance": 0,
-  "node": "g78c3c39e09c4afbd179c2da73190054fe97deedc",
-  "dirty": true,
-  "branch": "HEAD",
-  "node_date": "2026-07-09"
-}