warn-scraper 1.2.86__py3-none-any.whl → 1.2.88__py3-none-any.whl

warn/scrapers/co.py

@@ -123,7 +123,11 @@ def scrape(
         "Occupations Impacted": "occupations",
         "Occupations": "occupations",
         "Select the workforce area": "workforce_area",
+        "Total CO": "jobs",
+        "CO Layoffs": "jobs",
         "Total number of permanent layoffs": "permanent_job_losses",
+        "# permanent": "permanent_job_losses",
+        "# Permanent": "permanent_job_losses",
         "Total number of temporary layoffs": "temporary_job_losses",
         "Total number of furloughs": "furloughs",
         "Begin date of layoffs": "begin_date",

warn/scrapers/va.py

@@ -1,11 +1,12 @@
 import logging
 from pathlib import Path
 
-from bs4 import BeautifulSoup, Tag
-
 from .. import utils
 from ..cache import Cache
 
+# from bs4 import BeautifulSoup, Tag
+
+
 __authors__ = ["zstumgoren", "Dilcia19", "shallotly"]
 __tags__ = ["html", "csv"]
 __source__ = {
@@ -29,26 +30,37 @@ def scrape(
 
     Returns: the Path where the file is written
     """
+    # This scraper initially tried to get a CSV download link that was only for the most recent entries. The scraping part of that broke.
+    # It's now hard-coded to a particular download link with parameters that should get the full thing.
+
+    # This may break again, but this revised attempt has far fewer moving parts and actually fetches the complete data set.
+    # Blame Stucka in December 2024.
+
     # Get the WARN page
-    url = "https://www.vec.virginia.gov/warn-notices"
-    r = utils.get_url(url, verify=False)
-    html = r.text
+    # url = "https://www.vec.virginia.gov/warn-notices"
+    # url = "https://vec.virginia.gov/warn-notices?field_notice_date_value%5Bmin%5D%5Bdate%5D=1%2F1%2F1990&field_notice_date_value%5Bmax%5D%5Bdate%5D=&field_region_warn_tid=All"
+    # r = utils.get_url(url, verify=True)
+    # html = r.text
 
     # Save it to the cache
     cache = Cache(cache_dir)
-    cache.write("va/source.html", html)
+    # cache.write("va/source.html", html)
 
     # Parse out the CSV download link
-    soup = BeautifulSoup(html, "html.parser")
-    csv_link = soup.find("a", text="Download")
-    if isinstance(csv_link, Tag):
-        csv_href = csv_link["href"]
-    else:
-        raise ValueError("Could not find CSV link")
-    csv_url = f"https://www.vec.virginia.gov{csv_href}"
+    # soup = BeautifulSoup(html, "html.parser")
+    # csv_link = soup.find("a", text="Download")
+    # if isinstance(csv_link, Tag):
+    #     csv_href = csv_link["href"]
+    # else:
+    #     raise ValueError("Could not find CSV link")
+
+    # csv_href = "/warn-notices-csv.csv?"
+    # csv_url = f"https://www.vec.virginia.gov{csv_href}"
+
+    csv_url = "https://vec.virginia.gov/warn-notices-csv.csv?field_notice_date_value%5Bmin%5D%5Bdate%5D=1%2F1%2F1990&field_notice_date_value%5Bmax%5D%5Bdate%5D=&field_region_warn_tid=All"
 
     # Download it to the cache
-    cache.download("va/source.csv", csv_url, verify=False)
+    cache.download("va/source.csv", csv_url, verify=True)
 
     # Open it up as a list of rows
     csv_rows = cache.read_csv("va/source.csv")

{warn_scraper-1.2.86.dist-info → warn_scraper-1.2.88.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: warn-scraper
-Version: 1.2.86
+Version: 1.2.88
 Summary: Command-line interface for downloading WARN Act notices of qualified plant closings and mass layoffs from state government websites
 Home-page: https://github.com/biglocalnews/warn-scraper
 Author: Big Local News

{warn_scraper-1.2.86.dist-info → warn_scraper-1.2.88.dist-info}/RECORD

@@ -29,7 +29,7 @@ warn/scrapers/ak.py,sha256=h7BYMTV0whwWAPhbzVDVKMMoVCFphKly70aiTHabPq4,1847
 warn/scrapers/al.py,sha256=D0rT9GQ0vwfkRuveVAt-Po-T6b2TI1EPGeLOBy2m3_M,2240
 warn/scrapers/az.py,sha256=elGbue01Gjf_DQ66Wy9qqGIOJsiY-KIKJOVeft8pCXg,1447
 warn/scrapers/ca.py,sha256=VQOfjHXPCc-jYwh-EPGVVfnzvXB7pdmCt2uJ6QnMPRM,8600
-warn/scrapers/co.py,sha256=g076Zqe8XA8tbW03HP6-03mJV8fft1niHfa5Sy6me9A,7388
+warn/scrapers/co.py,sha256=fgeZj8UVtK0mHA07pH1z_wNA3QRSPltwK-Htoby8uJo,7540
 warn/scrapers/ct.py,sha256=HLMmBSFhT5Y3vZQUwRyCTxiG5BMQXTfG3SEj5rkQEL4,4771
 warn/scrapers/dc.py,sha256=_sHLnVqK_W90QqJb_W88yDlgPjoMl63LYZP3CJfdN9g,4484
 warn/scrapers/de.py,sha256=GyM92A-lFwZAfRxgbO-sIWhRfmBEKirzchaPIv-u0o4,1364
@@ -61,13 +61,13 @@ warn/scrapers/sd.py,sha256=_4R19Ybzsyx1PvcWV3_laJmJ3etrwVGfhNEQm6njwoA,1904
 warn/scrapers/tn.py,sha256=i1H7c09Ea3CDrTXqqRMLBMPT_34QtGA0-x7T8rm_j5Q,2945
 warn/scrapers/tx.py,sha256=watfR1gyN9w7nluiAOnnIghEmoq3eShNUzYSZ8SkZy4,4438
 warn/scrapers/ut.py,sha256=iUh38YIjbvv5MyyKacsiZNe8KjfdBeDaOf-qMQEF_kc,2245
-warn/scrapers/va.py,sha256=13lhkQrSkPGHEiWUuf1qiS890PWYE5gV-TgISpoiQnc,1711
+warn/scrapers/va.py,sha256=-QRIMPVIhBGDiKQOaMwwZbPtJxd1S2QwYX4Zxq1NNt0,2549
 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-1.2.86.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-warn_scraper-1.2.86.dist-info/METADATA,sha256=ywpbYFVG5StGGEjfIgHos1Sn5JTMBPrPoYhi5VBMSUE,2036
-warn_scraper-1.2.86.dist-info/WHEEL,sha256=Wyh-_nZ0DJYolHNn1_hMa4lM7uDedD_RGVwbmTjyItk,91
-warn_scraper-1.2.86.dist-info/entry_points.txt,sha256=poh_oSweObGlBSs1_2qZmnTodlOYD0KfO7-h7W2UQIw,47
-warn_scraper-1.2.86.dist-info/top_level.txt,sha256=gOhHgNEkrUvajlzoKkVOo-TlQht9MoXnKOErjzqLGHo,11
-warn_scraper-1.2.86.dist-info/RECORD,,
+warn_scraper-1.2.88.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+warn_scraper-1.2.88.dist-info/METADATA,sha256=-30KqUCkeCjeAa13tyECWG9PCHBxQhSPdbbhQ1rZGF4,2036
+warn_scraper-1.2.88.dist-info/WHEEL,sha256=Wyh-_nZ0DJYolHNn1_hMa4lM7uDedD_RGVwbmTjyItk,91
+warn_scraper-1.2.88.dist-info/entry_points.txt,sha256=poh_oSweObGlBSs1_2qZmnTodlOYD0KfO7-h7W2UQIw,47
+warn_scraper-1.2.88.dist-info/top_level.txt,sha256=gOhHgNEkrUvajlzoKkVOo-TlQht9MoXnKOErjzqLGHo,11
+warn_scraper-1.2.88.dist-info/RECORD,,