fix typos and spelling errors

.github/workflows/lint.yml

@@ -20,7 +20,7 @@ jobs:
         python-version: "3.9"
     - name: install poetry
       run: pip install poetry wheel
-    - name: install depdenencies
+    - name: install dependencies
       run: poetry install --only=dev
     - name: flake8 check
       run: poetry run flake8 scrapers scrapers_next

scrapers/az/bills.py

@@ -153,7 +153,7 @@ def scrape_actions(self, bill, page, self_chamber):
 
         for action in utils.action_map:
             if page[action] and utils.action_map[action]["name"] != "":
-                # sometimes intead of a date they placeholder with True
+                # sometimes instead of a date they placeholder with True
                 # see 2021 SB1308
                 if page[action] is True:
                     continue

scrapers/dc/bills.py

@@ -285,7 +285,7 @@ def scrape(self, session=None):
                                             v.vote("other", mem_name)
                                             other_count += 1
                                         else:
-                                            # Incase anything new pops up
+                                            # In case anything new pops up
                                             other_count += 1
                                             v.vote("other", mem_name)
 

scrapers/de/bills.py

@@ -51,7 +51,7 @@ def scrape(self, session=None):
 
     def filter_bills(self, items):
         """
-        Read through all bills on a page. If a bill has no subsitutes,
+        Read through all bills on a page. If a bill has no substitutes,
         yield it. If a bill does have substitutes, keep the highest-numbered
         substitute and only yield that Bill object.
         Bills may be amended (`BILL_ID w/ AMENDMENT ID` on the website),

scrapers/fl/bills.py

@@ -539,7 +539,7 @@ def process_page(self):
                         votes["no"].append(member)
                     else:
                         raise ValueError(
-                            "Unparseable vote found for {} in {}:\n{}".format(
+                            "Unparsable vote found for {} in {}:\n{}".format(
                                 member, self.source.url, line
                             )
                         )

scrapers/ia/bills.py

@@ -103,7 +103,7 @@ def scrape_prefiles(self, session):
                 elif ".pdf" in document_url:
                     media_type = "application/pdf"
                 bill.add_document_link(
-                    note="Backround Statement", url=document_url, media_type=media_type
+                    note="Background Statement", url=document_url, media_type=media_type
                 )
 
             bill.add_version_link(

scrapers/id/bills.py

@@ -218,7 +218,7 @@ def _split(string):
                     actor, date, row[2], session, bill_id, chamber, url
                 )
                 # bill.add_vote_event(vote)
-            # some td's text is seperated by br elements
+            # some td's text is separated by br elements
             if len(row[2]):
                 action = "".join(row[2].itertext())
             action = action.replace("\xa0", " ").strip()

scrapers/ma/bills.py

@@ -402,7 +402,7 @@ def scrape_house_vote(self, vote, vurl, supplement):
             self.info("No vote found in supplement for vote #%s" % supplement)
             return
 
-        # create list of independant items in vote_text
+        # create list of independent items in vote_text
         rows = vote_text.splitlines()
         lines = []
         for row in rows:

scrapers/md/bills.py

@@ -176,7 +176,7 @@ def parse_vote_pdf(self, vote_url, bill):
             if not any(
                 motion_keyword in motion.lower() for motion_keyword in motion_keywords
             ):
-                # This condition covers for the bad formating in SB 1260
+                # This condition covers for the bad formatting in SB 1260
                 motion = lines[page_index - 3]
             if not any(
                 motion_keyword in motion.lower() for motion_keyword in motion_keywords

scrapers/mi/events.py

@@ -90,7 +90,7 @@ def scrape_event_page(self, url, chamber):
 
         # The MI pages often contain broken markup for line breaks in the agenda
         # like </BR>. This gets stripped in text_content and we lose the information
-        # needed to seperate out agenda sections.
+        # needed to separate out agenda sections.
         # So instead, pull out the raw HTML, break it, then parse it.
         agenda = page.xpath("//td[contains(., 'Agenda')]/following-sibling::td")[0]
         agenda_html = lxml.etree.tostring(agenda, encoding="unicode")

scrapers/mt/committees.py

@@ -113,7 +113,7 @@ def _fix_house_text(self, filename):
 
         The best solution to this is to throw out the offending text,
         and replace it with the correct text. The third and fourth
-        columns are joint comittees that are scraped from the Senate
+        columns are joint committees that are scraped from the Senate
         document, so the only column that needs to be inserted this way
         is the second.
         """

scrapers/pr/bills.py

@@ -20,7 +20,7 @@ class NoSuchBill(Exception):
     ("Enviado al Gobernador", "executive", "executive-receipt"),
     ("Veto", "executive", "executive-veto"),
     ("Veto de Bolsillo", "executive", "executive-veto"),
-    # comissions give a report but sometimes they dont do any amendments and
+    # commissions give a report but sometimes they dont do any amendments and
     # leave them as they are.
     # i am not checking if they did or not. but it be easy just read the end and
     # if it doesn't have amendments it should say 'sin enmiendas'

scrapers/pr/votes.py

@@ -110,7 +110,7 @@ def scrape_journal(self, url, chamber, session, date):
                     result = "pass"
                 else:
                     result = "fail"
-                    msg = "Voting result {} not guarenteed to be 'fail'. Take a look.".format(
+                    msg = "Voting result {} not guaranteed to be 'fail'. Take a look.".format(
                         vote_result["result"]
                     )
                     self.logger.warning(msg)

scrapers/sd/events.py

@@ -93,7 +93,7 @@ def scrape(self):
             # Because the list of docs isn't ordered, We need to loop through this list multiple times.
             # once to grab DocumentTypeId = 5, which are the agendas for the actual meetings
             # then after we've created the events, again for DocumentTypeId = 4, which are the minutes
-            # we can skip the other DocumentTypeIds becase they're included in the /Documents endpoint,
+            # we can skip the other DocumentTypeIds because they're included in the /Documents endpoint,
             # or audio which is duplicated in DocumentTypeId 5
             for row in documents:
                 if row["NoMeeting"] is True:

scrapers/usa/votes.py

@@ -243,7 +243,7 @@ def scrape_senate_vote(self, session, period, roll_call):
         roll_call = page.xpath("//roll_call_vote/vote_number/text()")[0]
         vote_id = "us-{}-upper-{}".format(when.year, roll_call)
 
-        # note: not everthing the senate votes on is a bill, this is OK
+        # note: not everything the senate votes on is a bill, this is OK
         # non bills include nominations and impeachments
         doc_type = page.xpath("//roll_call_vote/document/document_type/text()")[0]
 

scrapers/vi/bills.py

@@ -52,11 +52,11 @@
     ("COCHPY&R", "COMMITTEE OF CULTURE, HISTORIC PRESERVATION, YOUTH & RECREATION"),
     ("COEDA&P", "COMMITTEE OF ECONOMIC DEVELOPMENT, AGRICULTURE & PLANNING"),
     ("COE&WD", "COMMITTEE OF EDUCATION & WORKFORCE DEVELOPMENT"),
-    ("HEALTH", "COMMITTEE OF ENERGY & ENVIROMENTAL PROTECTION"),
+    ("HEALTH", "COMMITTEE OF ENERGY & ENVIRONMENTAL PROTECTION"),
     ("COF", "COMMITTEE OF FINANCE"),
     ("COHHHS&VA", "COMMITTEE OF HEALTH, HOSPITAL & HUMAN SERVICES"),
     ("COHSJ&PS", "COMMITTEE OF HOMELAND SECURITY, PUBLIC SAFETY & JUSTICE"),
-    ("PUBLICWRKS", "COMMITTEE OF HOUSING, PUBLIC WORKS & WASTE MANAGMENT"),
+    ("PUBLICWRKS", "COMMITTEE OF HOUSING, PUBLIC WORKS & WASTE MANAGEMENT"),
     ("RULJUD", "COMMITTEE OF RULES & JUDICIARY"),
     ("WHOLE", "COMMITTEE OF THE WHOLE"),
     ("GOVSERV", "COMMITTEE ON GOVERNMENT SERVICES, CONSUMER AND VETERANS AFFAIRS"),

scrapers/wi/bills.py

@@ -268,7 +268,7 @@ def parse_sponsors(self, bill, action, chamber):
                 line,
             )
             if not match:
-                # So far, the only one that doens't match is
+                # So far, the only one that doesn't match is
                 # http://docs.legis.wisconsin.gov/2011/proposals/ab568
                 # In the following format:
                 # Introduced by Representatives Krusick and J. Ott, by ... ;

scrapers/wv/events.py

@@ -161,7 +161,7 @@ def scrape_meeting_page(self, url):
 
     def clean_date(self, when):
         # Remove all text after the third comma to make sure no extra text
-        # is included in the date. Required to correctly parse texxt like this:
+        # is included in the date. Required to correctly parse text like this:
         # "Friday, March 3, 2023, Following wrap up of morning agenda"
         when = ",".join(when.split(",")[:2])
 

scrapers_next/de/committees.py

@@ -77,7 +77,7 @@ def process_page(self):
 
 
 class CommitteeList(HtmlPage):
-    # This page is scraped before geting the json data because the current
+    # This page is scraped before getting the json data because the current
     # session id needs to be extracted. This page has a <select> element where
     # the first <option> inside of it has the required session id.
     source = "https://legis.delaware.gov/Committees"

scrapers_next/ny/people.py

@@ -51,7 +51,7 @@ def block_to_text(elem):
 
 def parse_address_lines(text):
     """
-    a fairly common occurence, a bunch of lines like
+    a fairly common occurrence, a bunch of lines like
     addr line 1
     addr line 2
     addr line 3?

scripts/people-update.sh

@@ -28,7 +28,7 @@ fi
 rm -rf "${SCRIPT_DIR}/../_scrapes/${TODAY}"
 mkdir -p "${SCRIPT_DIR}/../_scrapes"
 
-echo "ensuring depdendencies are up to date"
+echo "ensuring dependencies are up to date"
 poetry install
 
 echo "Cloning people repo..."