warn-scraper 1.2.151.dev0__py3-none-any.whl → 1.2.153.dev0__py3-none-any.whl

warn/pdfrodent/pdfrodent.py

@@ -0,0 +1,361 @@
+import json
+import logging
+import re
+
+import camelot  # pip install camelot-py==1.0.9 for now
+
+logger = logging.getLogger(__name__)
+
+
+def clean_cell(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 ""
+
+    # Standardize whitespace
+    clean_text = re.sub(r"\s+", " ", text).strip()
+
+    return clean_text
+
+
+def clean_row(row: list):
+    """Clean up text from a list of strings.
+
+    args:
+        row (list): list of strings
+    returns:
+        line (list): list of strings, each with minimal whitespace
+    """
+    line: list = []
+    for cell in row:
+        line.append(clean_cell(cell))
+    return line
+
+
+def is_empty(row: list) -> bool:
+    """
+    Check if a row has no populated cells.
+
+    Keyword arguments:
+    row -- the row to check
+
+    Returns: True if the row is empty, False otherwise
+    """
+    return len(list(filter(None, row))) == 0
+
+
+def is_mostly_empty(row: list) -> bool:
+    """
+    Check if a row has few populated cells. Used to determine if carried over from a previous page.
+
+    Keyword arguments:
+    row -- the row to check
+
+    Returns: True if the row is mostly empty, False otherwise
+    """
+    return len(list(filter(None, row))) <= 2
+
+
+def has_content(value):
+    """Check if a particular value has any content, e.g. is it a null or an empty string."""
+    if value is list:
+        content = True
+    elif value is dict:
+        content = True
+    elif value is None:
+        content = False
+    else:
+        value = str(value).strip()
+        if len(value) > 0:
+            content = True
+        else:
+            content = False
+    return content
+
+
+def count_data_items(row: list, prefixes=None) -> int:
+    """
+    Count number of non-blank non-null data items in a row that aren't an internal variable.
+
+    Args:
+        row (list of dicts): The row to check
+        prefixes (list) optional: If not provided, will skip data items beginning with ["int_", "_int"]. To empty pass an empty list.
+    Returns:
+        Integer of how many non-blank non-internal data items there are
+    """
+    good_items = 0
+    if not prefixes:
+        prefixes = ["int_", "_int_"]
+    for field in row:
+        goodfieldname = True
+        for prefix in prefixes:
+            if field.startswith(prefix):
+                goodfieldname = False
+        if goodfieldname:
+            if has_content(row[field]):
+                good_items += 1
+    return good_items
+
+
+def drop_thin_rows(rows: list, cutnumber: int, prefixes=None):
+    """
+    Drop rows with an improperly low count of valid entries, after filtering out prefixed rows of safe data.
+
+    Args:
+        row: List of dicts
+        cutnumber: Cut rows with X or fewer full items. x + 1, then, would be the minimum count of good.
+        prefixes: list, optional. If not provided will neglect to count data items beginning with ["int_", "_int_"]. To empty pass an empty list.
+    Returns:
+        line: List of dics
+    """
+    lines = []
+    if not prefixes:
+        prefixes = ["int_", "_int_"]
+    for row in rows:
+        if count_data_items(row, prefixes=prefixes) > cutnumber:
+            lines.append(row)
+    return lines
+
+
+internal_documentation_such_as_it_is = """
+OK, this is going to be messy. The higher-level overview:
+We get lists of strings from the PDF, an ostensible PDF row.
+
+Some of these lists are going to be headers. The headers, of course, need to be detected initially.
+
+And sometimes the headers show up as their own table, with nothing else.
+If this is the case, they need to be applied as the headers to subsequent tables.
+
+But headers can also repeat across pages, so we need to detect them.
+
+To add to the fun, each of these rows from the PDF may be just part of another logical row,
+from when cells are divided horizontally to hold multiple data points.
+
+We need to detect those fragmentary lines, mostly by checking to see if most cells are empty.
+
+If they're a fragment of a header, we need to track it somehow and build a structure to hold the fragment.
+And remember header fragments may occur on multiple pages with multipage headers.
+That means we need to build an initial structure to hold the headers, then skip some rows if we see the header again.
+
+For non-header fragments, we need to append the data to the previous line in an appropriate data structure.
+
+But wait! There's more!
+
+PDF data tends to be really dirty, lots of junky white space.
+
+Some people will use multiline data to show multiple data points in a single cell, such as Company name<newline>, City, State ZIP.
+If we strip off white space, we're losing a way to segregate and process that data later. So we can't clean it up until later.
+Unless it's for fragmentary rows, because we need to know that they're fragmentary and white space will wreck the count.
+
+And of course lots of rows are entirely white space, just blank data rows left in a PDF. Those we just drop.
+
+To sum up:
+Just about every PDF row can be
+An orphaned header, alone in the table
+A full header row
+A fragmentary header
+A full data row
+A fragmentary data row
+A blank row
+
+We need many little trackers to go through here and figure out what we're looking at.
+
+We need code to clean up whitespace in cells and rows.
+
+We need a function to delete rows with fewer than a certain number of data points (e.g., contents of a summary table).
+
+We need a function that allows us to standardize header names.
+
+We probably want code that tells us what PDF this is pulled from, on which row.
+"""
+
+
+def parse_pdf(pdffile: str, field_fixes: dict | None = None):
+    """Parse a PDF file to extract data from tables.
+
+    Args:
+        Filename (string)
+        field_fixes (string or dict): If supplied, a dictionary of header lookup values with values of the target name
+
+    Returns:
+        filelist: A list of dictionaries of data rows keyed to headers
+        filerowholder: Debugging data showing how row types were determined
+    """
+    if not field_fixes:
+        logger.debug(
+            "No 'field_fixes' variable submitted to pdfrodent.parse_pdf function."
+        )
+        field_fixes = {}
+    else:
+        logger.debug(f"{len(field_fixes):,} field_fixes to be used to clean headers.")
+    filelist = []
+    filerowholder = []
+    logger.debug(f"Opening {pdffile} for PDF parsing")
+    tables = camelot.read_pdf(pdffile, pages="all")
+    orphanedheader = False
+    orphanholder = None
+    for tableindex, table in enumerate(tables):
+        locallist: list = []
+        logger.debug(f"Processing table {tableindex} of {pdffile}")
+        filerowholder.append(f"Processing table {tableindex} of {pdffile}")
+        rawheader = None
+        headerfirst = []
+        headersupplement: dict = {}
+        isheader = True
+        seendata = False
+        logger.debug(
+            f"Processing table {tableindex} with {len(table.rows)} of {pdffile}"
+        )
+
+        # If the table has only one row, it's a stray header and should be used with the next table.
+        if len(table.rows) == 1:
+            logger.debug("\tOrphaned header detected!")
+            filerowholder.append("\tOrphaned header detected!")
+            orphanedheader = True
+            patchedheaders = []
+            rawheader = table.data[0]
+            for item in clean_row(rawheader):
+                if item in field_fixes:
+                    patchedheaders.append(field_fixes[item])
+                else:
+                    logger.debug(
+                        f"New header type found: {item}, not in {' '.join(sorted(list(field_fixes.keys())))}"
+                    )
+                    patchedheaders.append(item)
+            orphanholder = {
+                "rawheader": rawheader,
+                "patchedheaders": patchedheaders,
+            }
+            logger.debug(f"{orphanholder}")
+            filerowholder.append(f"{orphanholder}")
+        # If there are multiple rows, there are a bunch of possibilities we need to poke ...
+        else:
+            # If we have a header from a one-row table, prepare to use the orphaned header
+            if orphanedheader:
+                isheader = True
+                rawheader = orphanholder["rawheader"]  # type: ignore
+                headerfirst = orphanholder["patchedheaders"]  # type: ignore
+
+            for rowindex, row in enumerate(table.data):
+                filerowholder.append(row)
+                line: dict = {}  # rows in, lines out
+                # If it's the first row in a table and we don't have an orphaned header,
+                # it's an index row
+                if rowindex == 0 and not orphanedheader:
+                    rawheader = row
+                    patchedheaders = []
+                    for item in clean_row(rawheader):
+                        if item in field_fixes:
+                            patchedheaders.append(field_fixes[item])
+                        else:
+                            logger.debug(
+                                f"New header type found: {item}, not in {' '.join(sorted(list(field_fixes.keys())))}"
+                            )
+                            patchedheaders.append(item)
+                    headerfirst = patchedheaders
+                    isheader = True
+                    filerowholder.append("\tIndex row!")
+
+                elif row == rawheader:  # Later instance of a page header
+                    isheader = True
+                    filerowholder.append("\tRepeated header")
+
+                # Drop blank rows entirely
+                elif is_empty(clean_row(row)):
+                    filerowholder.append("\tEmpty row")
+                    pass
+
+                # Handle fragmentary records
+                elif is_mostly_empty(clean_row(row)):
+                    filerowholder.append("\tMostly empty row!")
+                    if not seendata:  # Is this part of the initial header?
+                        filerowholder.append("\tMostly empty row, haven't seen data")
+                        for cellindex, cell in enumerate(row):
+                            cleancell = clean_cell(cell)
+                            if len(cleancell) > 0:  # If we have good data
+                                fieldname = f"supplement{cellindex}"
+                                headersupplement[fieldname] = None  # type: ignore
+                            isheader = False
+                            orphanedheader = False
+
+                    else:  # seenheader
+                        if isheader:  # Supplement to a header on a latter page
+                            filerowholder.append(
+                                "\tMostly empty row, seems to be appending to a header"
+                            )
+                            for cellindex, cell in enumerate(row):
+                                cleancell = clean_cell(cell)
+                                if len(cleancell) > 0:  # If we have good data
+                                    if cleancell not in headersupplement:
+                                        headersupplement[cellindex] = headersupplement
+                                        logger.debug(
+                                            f"Added {cleancell} to headersupplement, which now holds: {headersupplement}"
+                                        )
+                            isheader = False
+
+                        else:  # Not a header, have seenheader; must be a regular row supplement
+                            orphanedheader = False
+                            isheader = False
+                            filerowholder.append(
+                                "\tMostly empty row, seems to be detailed info for a regular row"
+                            )
+                            for cellindex, cell in enumerate(row):
+                                cleancell = clean_cell(cell)
+                                if len(cleancell) > 0:  # If we have good data
+                                    if cellindex in headersupplement:
+                                        fieldname = headersupplement[cellindex]  # type: ignore
+                                    else:
+                                        fieldname = f"supplement_{cellindex}"
+                                        logger.warning(
+                                            f"Found {fieldname} as {cleancell} but not located in supplemental headers: {headersupplement}"
+                                        )
+                                        if fieldname in field_fixes:
+                                            logger.debug(
+                                                f"Shifting cell with {fieldname} to {field_fixes[fieldname]}"
+                                            )
+                                            fieldname = field_fixes[fieldname]
+                                    locallist[-1][
+                                        fieldname
+                                    ] = cleancell  # Add it to the previous line
+                        isheader = False
+
+                else:
+                    # It's not an orphaned header
+                    # It's not the initial header
+                    # It's not a supplemental header
+                    # It's not an empty row
+                    # It's not a supplemental data row
+                    # We ... actually have a regular data row here.
+                    orphanedheader = False
+                    filerowholder.append("\tSeems to be a regular row.")
+                    isheader = False
+                    seendata = True
+                    for cellindex, cell in enumerate(row):
+                        line[headerfirst[cellindex]] = clean_cell(cell)
+                    filerowholder.append(f"\t\t{line}")
+                    locallist.append(line)
+
+            report = table.parsing_report
+
+            for lineindex, line in enumerate(locallist):
+                line["_int_accuracy"] = report["accuracy"]
+                line["_int_pdf_filename"] = pdffile.split("/")[-1].split("\\")[-1]
+                line["_int_page"] = report["page"]
+                line["_int_table_number"] = report["order"]
+                line["_int_raw_fields"] = json.dumps(list(line.values()))
+                line["_int_data_items"] = count_data_items(line)  # type: ignore
+                if "Event Number" in line:
+                    line["Event Number"] = line["Event Number"].replace("\n", "")
+
+                locallist[lineindex] = line  # Save it back
+
+        filelist.extend(locallist)
+    return (filelist, filerowholder)

warn/scrapers/al.py

@@ -32,11 +32,15 @@ def scrape(
     Returns: the Path where the file is written
     """
     output_csv = data_dir / "al.csv"
-    page = utils.get_url("https://www.madeinalabama.com/warn-list/")
+    # page = utils.get_url("https://www.madeinalabama.com/warn-list/")
+    # URL change in June 2026, maybe led to a HTTP 415 error
+    page = utils.get_url("https://workforce.alabama.gov/warn-list/")
+
     # can't see 2020 listings when I open web page, but they are on the summary in the google search
     soup = BeautifulSoup(page.text, "html.parser")
     table = soup.find_all("table")  # output is list-type
     table_rows = table[0].find_all("tr")
+    logger.debug(f"{len(table_rows):,} total table rows (including header) found")
     # Handle the header
     raw_header = table_rows.pop(0)
     header_row = _extract_fields_from_row(raw_header, "th")

warn/scrapers/ms.py

@@ -0,0 +1,150 @@
+import json
+import logging
+from pathlib import Path
+
+from pyquery import PyQuery as pq
+
+from warn.pdfrodent import pdfrodent as pdfrodent
+
+from .. import utils
+from ..cache import Cache
+
+__authors__ = ["Ash1R", "stucka"]
+__tags__ = ["pdf"]
+__source__ = {
+    "name": "Mississippi Department of Employment Security",
+    "url": "https://mdes.ms.gov/information-center/warn-information/",
+}
+
+logger = logging.getLogger(__name__)
+want_debugging_file = True
+
+
+def scrape(
+    data_dir: Path = utils.WARN_DATA_DIR,
+    cache_dir: Path = utils.WARN_CACHE_DIR,
+) -> Path:
+    """
+    Scrape data from Mississippi.
+
+    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
+    """
+    cache = Cache(cache_dir)
+    remoteurl = __source__["url"]
+    urlprefix = remoteurl.split(".gov")[0] + ".gov"
+
+    html = utils.get_url(remoteurl).text
+    cache.write("ms/index.html", html)
+
+    content = pq(html)("div#page_content")
+    anchors = pq(content)("a")
+
+    # Parse HTML to identify relevant PDFs
+    urlswanted = []
+    for anchor in anchors:
+        href = pq(anchor).attr("href")
+        remoteurl = href
+        if "http" not in remoteurl:
+            remoteurl = urlprefix + remoteurl
+        if remoteurl.endswith(".pdf"):
+            if not remoteurl.endswith("map.pdf"):
+                urlswanted.append(remoteurl)
+
+    # Get the files. The five first-listed files, we want fresh.
+    # That should cover every quarter in the latest year, and one quarter of the previous year, at least.
+    for i, urlwanted in enumerate(urlswanted):
+        basefilename = urlwanted.split("/")[-1]
+        localfilename = cache_dir / f"ms/{basefilename}"
+        if i <= 4:  # Get the five newest files to ensure proper overlap
+            logger.debug(f"Fetching fresh copy of {localfilename}")
+            utils.save_if_good_url(localfilename, urlwanted)
+        else:
+            logger.debug(f"Getting copy of {localfilename} if needed")
+            utils.fetch_if_not_cached(localfilename, urlwanted)
+
+    pdffiles = sorted(cache.files(subdir="ms/", glob_pattern="*.pdf"))
+
+    headerfixes = {
+        "": "blank_entry",
+        "# Affected": "affected",
+        "# Of Notices Received": "notices_received",
+        "City": "city",
+        "Company Name": "company",
+        "Company Name (City) (County)": "company",
+        "Company Name (City) (County) (Zip)": "company",
+        "Company Name City (County)": "company",
+        "Company Name City, (County)": "company",
+        "Company Name, City (County)": "company",
+        "Company Name, City, County": "company",
+        "County": "county",
+        "Date of Action": "date_effective",
+        "Date of Notice": "date_notice",
+        "Date of WARN Notice": "date_notice",
+        "Event Number": "event_number",
+        "NAICS CODE & Description": "naics",
+        "NAICS CODE – Description": "naics",
+        "Notices Received": "notices_received",
+        "Number Of Notices Received": "notices_received",
+        "Number Of Notices Received October 2024 – December 2024": "notices_received",
+        "Number Affected": "affected",
+        "Reason / Comments": "reason",
+        "Reason – Comments": "reason",
+        "Type of Action": "action_type",
+        "Type of Action # Affected": "action_type",
+        "T ypes of Notice": "notice_types",
+        "T ypes of Notices Received": "notice_types",
+        "Type of Notice": "notice_types",
+        "Types of Notice": "notice_types",
+        "Types of Notices": "notice_types",
+        "Types of Notices Received": "notice_types",
+        "Workforc e Area": "workforce_area",
+        "Workforce Area": "workforce_area",
+        "_int_accuracy": "_int_accuracy",
+        "_int_data_items": "_int_data_items",
+        "_int_page": "_int_page",
+        "_int_pdf_filename": "_int_pdf_filename",
+        "_int_raw_fields": "_int_raw_fields",
+        "_int_table_number": "_int_table_number",
+        "supplement_0": "supplement_0",
+        "supplement_1": "supplement_1",
+        "supplement_2": "supplement_2",
+        "supplement_5": "affected",  # Only carries from 2025sq2
+    }
+
+    masterlist = []
+    rowholder = []
+    for pdffile in pdffiles:
+        locallist, localrows = pdfrodent.parse_pdf(pdffile, headerfixes)
+        masterlist.extend(locallist)
+        rowholder.extend(localrows)
+
+    # Identify all header elements, even in the ones we're about to remove.
+    allheaders = set()
+    for row in masterlist:
+        for item in row:
+            allheaders.add(item)
+    text = ""
+    for item in sorted(allheaders):
+        text += f"\t\t'{item}': ,\n"
+    with open(Path(cache_dir) / "ms/allheaders.txt", "w") as outfile:
+        outfile.write(text)
+
+    targetfilename = data_dir / "ms.csv"
+    logger.debug(f"Found {len(masterlist):,} extracted rows from the PDFs.")
+    cleaned = pdfrodent.drop_thin_rows(masterlist, 6)
+    logger.debug(
+        f"After filtering out thin rows, we have {len(cleaned):,} rows of data meeting standards."
+    )
+    # utils.write_disparate_dict_rows_to_csv(targetfilename, masterlist)
+    utils.write_disparate_dict_rows_to_csv(targetfilename, cleaned)
+
+    if want_debugging_file:
+        with open(Path(cache_dir) / "ms/debugging.txt", "w") as outfile:
+            for row in rowholder:
+                outfile.write(json.dumps(row) + "\r\n")
+
+    return targetfilename

warn/utils.py

@@ -213,7 +213,7 @@ def write_rows_to_csv(output_path: Path, rows: list, mode="w"):
         mode (str): the mode to be used when opening the file (default 'w')
     """
     create_directory(output_path, is_file=True)
-    logger.debug(f"Writing {len(rows)} rows to {output_path}")
+    logger.debug(f"Writing {len(rows):,} rows to {output_path}")
     with open(output_path, mode, newline="", encoding="utf-8") as f:
         writer = csv.writer(f)
         writer.writerows(rows)
@@ -230,7 +230,7 @@ def write_dict_rows_to_csv(output_path, headers, rows, mode="w", extrasaction="r
         extrasaction (str): what to do if the if a field isn't in the headers (default 'raise')
     """
     create_directory(output_path, is_file=True)
-    logger.debug(f"Writing {len(rows)} rows to {output_path}")
+    logger.debug(f"Writing {len(rows):,} rows to {output_path}")
     with open(output_path, mode, newline="") as f:
         # Create the writer object
         writer = csv.DictWriter(f, fieldnames=headers, extrasaction=extrasaction)
@@ -243,22 +243,40 @@ def write_dict_rows_to_csv(output_path, headers, rows, mode="w", extrasaction="r
             writer.writerow(row)
 
 
-def write_disparate_dict_rows_to_csv(output_path, rows, mode="w"):
+def write_disparate_dict_rows_to_csv(
+    output_path, rows, mode="w", prefixes: None | list = None
+):
     """Write the provided list of dictionaries to the provided path as comma-separated values, while determining a header.
 
     Args:
         output_path (Path): the Path were the result will be saved
         rows (list): the list of dictionaries to be saved; can have disparate dict keys
         mode (str): the mode to be used when opening the file (default 'w')
+        prefixes(list|None): text strings that determine whether fields should arrive after other fields.
+            Send an empty list, [], to run without any prefixes.
+            Send None or don't send to use default prefixes of _int_ and int_
     """
+    if not prefixes:
+        prefixes = ["int_", "_int_"]
+    logger.debug(f"Writing {(len(rows)+1):,} rows to {output_path}")
     create_directory(output_path, is_file=True)
-    headers: set = set()  # Get all the potential header names
+    headers: list = []  # We want to preserve order, and set won't do it.
+    headerextras: list = []  # stuff that should be at the right of the field list
     for row in rows:
         for item in row:
-            headers.add(item)
-    headers = list(sorted(headers))
-    logger.debug(f"Found {len(headers):,} header entries in list of dicts.")
-    logger.debug(f"Writing {len(rows)} rows to {output_path}")
+            if item not in headers and item not in headerextras:
+                prefixhere = False
+                for prefix in prefixes:
+                    if item.startswith(prefix):
+                        prefixhere = True
+                if prefixhere:
+                    headerextras.append(item)
+                else:
+                    headers.append(item)
+    logger.debug(
+        f"Found {(len(headers) + len(headerextras)):,} header entries in the supplied list of dicts."
+    )
+    headers.extend(headerextras)
     with open(output_path, mode, newline="") as outfile:
         # Create the writer object
         writer = csv.writer(outfile)

{warn_scraper-1.2.151.dev0.dist-info → warn_scraper-1.2.153.dev0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: warn-scraper
-Version: 1.2.151.dev0
+Version: 1.2.153.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-1.2.151.dev0.dist-info → warn_scraper-1.2.153.dev0.dist-info}/RECORD

@@ -2,7 +2,9 @@ warn/__init__.py,sha256=A07JFY1TyaPtVIndBa7IvTk13DETqIkLgRdk0A-MCoE,85
 warn/cache.py,sha256=QBSHycchvRTkOQfHptOtZeTYiPgLP383jS8MTiGln_c,5969
 warn/cli.py,sha256=ZqyJwICdHFkn2hEgbArj_upbElR9-TSDlYDqyEGeexE,2019
 warn/runner.py,sha256=oeGRybGwpnkQKlPzRMlKxhsDt1GN4PZoX-vUwrsPgos,1894
-warn/utils.py,sha256=eF7lI2ObsagxBYPcOZc--DJp_vxA3Jl4nCcBs4C8zmc,12253
+warn/utils.py,sha256=-JF8DnSg-80CbCIswM-rtB0CWf9zSVU56iJNpRw3V-o,13086
+warn/pdfrodent/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+warn/pdfrodent/pdfrodent.py,sha256=IajvUyzVuUlph7F3LqaPU0HxDCkHb8YfnP1js4vOoTs,14632
 warn/platforms/__init__.py,sha256=wIZRDf4tbTuC8oKM4ZrTAtwNgbtMQGzPXMwDYCFyrog,81
 warn/platforms/job_center/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 warn/platforms/job_center/cache.py,sha256=yhA3sE46lNFg8vEewSoRYVByi0YSlkBiKm7qoSUiTdM,1868
@@ -11,7 +13,7 @@ warn/platforms/job_center/urls.py,sha256=IWhpuzN_xcNdHh23GbZPGvuHCsMcmb03qx3pRn1
 warn/platforms/job_center/utils.py,sha256=HdUKgKirmpPP7e4Cu_ZyB3zPVS_p-_ylo-lXFhxK2QM,5696
 warn/scrapers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 warn/scrapers/ak.py,sha256=h7BYMTV0whwWAPhbzVDVKMMoVCFphKly70aiTHabPq4,1847
-warn/scrapers/al.py,sha256=D0rT9GQ0vwfkRuveVAt-Po-T6b2TI1EPGeLOBy2m3_M,2240
+warn/scrapers/al.py,sha256=XSDEGC7F6_3GZ2m_uSiIG-1v8jMNH9pw_wNUCZyaMK0,2460
 warn/scrapers/az.py,sha256=elGbue01Gjf_DQ66Wy9qqGIOJsiY-KIKJOVeft8pCXg,1447
 warn/scrapers/ca.py,sha256=VQOfjHXPCc-jYwh-EPGVVfnzvXB7pdmCt2uJ6QnMPRM,8600
 warn/scrapers/co.py,sha256=83OdikIrWGxt22mlI-_zLSNqJg1NO5C2Xjm3FF6DPYY,18252
@@ -32,6 +34,7 @@ warn/scrapers/md.py,sha256=hwgxXQnhyBWm8qF1dvxIThAX1MkrZbXLwRI9inO5t8g,4060
 warn/scrapers/me.py,sha256=q36F4yJ7hvZsLayA3uBS1romo4X3Qf-sEi2Y7LAQCi8,1172
 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/ne.py,sha256=JawuGJ3tCKvMd-N-p03gnltB4rol4QUJshMk2oyMPO4,4143
 warn/scrapers/nj.py,sha256=nwbMbeQuUJbYRVoyUyKZBmNqvqsXu3Habt-10r8DvZE,2230
@@ -51,9 +54,9 @@ 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-1.2.151.dev0.dist-info/licenses/LICENSE,sha256=ZV-QHyqPwyMuwuj0lI05JeSjV1NyzVEk8Yeu7FPtYS0,585
-warn_scraper-1.2.151.dev0.dist-info/METADATA,sha256=AfbK5daYq_1v82cikgTIXPS7TsXjZgksMWwkDzahI0o,1780
-warn_scraper-1.2.151.dev0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
-warn_scraper-1.2.151.dev0.dist-info/entry_points.txt,sha256=poh_oSweObGlBSs1_2qZmnTodlOYD0KfO7-h7W2UQIw,47
-warn_scraper-1.2.151.dev0.dist-info/top_level.txt,sha256=dZfms6N3kqVXufiPOo7YqOrAcUtYfNH_oyGvYUk9FB4,5
-warn_scraper-1.2.151.dev0.dist-info/RECORD,,
+warn_scraper-1.2.153.dev0.dist-info/licenses/LICENSE,sha256=ZV-QHyqPwyMuwuj0lI05JeSjV1NyzVEk8Yeu7FPtYS0,585
+warn_scraper-1.2.153.dev0.dist-info/METADATA,sha256=wEonbrS1LWIOVFTuLq75_rlLbDGb2g3-7w30N1x_JAc,1780
+warn_scraper-1.2.153.dev0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+warn_scraper-1.2.153.dev0.dist-info/entry_points.txt,sha256=poh_oSweObGlBSs1_2qZmnTodlOYD0KfO7-h7W2UQIw,47
+warn_scraper-1.2.153.dev0.dist-info/top_level.txt,sha256=dZfms6N3kqVXufiPOo7YqOrAcUtYfNH_oyGvYUk9FB4,5
+warn_scraper-1.2.153.dev0.dist-info/RECORD,,