Merge branch 'master' of github.com:scrapd/scrapd into issues/106/dec…

…eased-field

scrapd/cli/cli.py

@@ -32,13 +32,11 @@
     show_default=True,
 )
 @click.option('--from', 'from_', help='start date')
-@click.option('--gcontributors', help='comma separated list of contributors')
-@click.option('--gcredentials', type=click.Path(), help='path of the google credentials file')
 @click.option('--pages', default=-1, help='number pages to process')
 @click.option('--to', help='end date')
 @click.option('-v', '--verbose', count=True, help='adjust the log level')
 @click.pass_context
-def cli(ctx, format_, from_, gcontributors, gcredentials, pages, to, verbose):  # noqa: D403
+def cli(ctx, format_, from_, pages, to, verbose):  # noqa: D403
     """Retrieve APD's traffic fatality reports."""
     ctx.obj = {**ctx.params}
     ctx.auto_envvar_prefix = 'VZ'

scrapd/core/apd.py

@@ -306,9 +306,13 @@ def parse_name(name):
     :return: a dictionary representing just the victim's first and last name
     :rtype: dict
     """
+    GENERATIONAL_TITLES = ['jr', 'jr.', 'sr', 'sr.']
     d = {}
     try:
-        d["last"] = name[-1].replace(',', '')
+        for i in range(1, len(name)):
+            d["last"] = name[-i].replace(',', '')
+            if d["last"].lower() not in GENERATIONAL_TITLES:
+                break
         d["first"] = name[0].replace(',', '')
     except (IndexError, TypeError):
         pass
@@ -742,7 +746,15 @@ async def fetch_and_parse(session, url):
 
 
 async def async_retrieve(pages=-1, from_=None, to=None):
-    """Retrieve fatality data."""
+    """
+    Retrieve fatality data.
+
+    :param str pages: number of pages to retrieve or -1 for all
+    :param str from_: the start date
+    :param str to: the end date
+    :return: the list of fatalities and the number of pages that were read.
+    :rtype: tuple
+    """
     res = {}
     page = 1
     has_entries = False

tests/core/test_apd.py

@@ -344,7 +344,11 @@ def test_parse_deceased_field_00(deceased, expected):
     }),
     (None, {
         'first': None,
-        'last': None
+        'last': None,
+    }),
+    (['Carlos', 'Cardenas', 'Jr.'], {
+        'first': 'Carlos',
+        'last': 'Cardenas',
     }),
 ))
 def test_parse_name(name, expected):