Formatting and README changes

Author: king-millez

README.md

@@ -1,11 +1,11 @@
-# Aus Bills
+# ausbills
 
-🇦🇺 This is a package is for obtaining parliament bills for Australian governments.
+🇦🇺 This is a package is for obtaining parliament bills for Australian parliaments.
 
-## Install via pip3
+## Install via pip
 
 ```
-pip3 install ausbills
+pip install ausbills
 ```
 
 ---
@@ -18,11 +18,11 @@ Most parliaments host their bills online in 2 forms:
 
 1. A table with a small amount of data about each bill
 
-    ![ACT bill list](.github/img/ACT_bill_list.PNG)
+   ![ACT bill list](.github/img/ACT_bill_list.PNG)
 
 2. Individual pages with all the info for a given bill.
 
-    ![ACT bill](.github/img/ACT_bill.PNG)
+   ![ACT bill](.github/img/ACT_bill.PNG)
 
 `ausbills` gives you access to all of this information.
 

ausbills/__init__.py

@@ -1,3 +1,3 @@
 from ausbills.log import get_logger
 
-log = get_logger('ausbills')
+log = get_logger("ausbills")

ausbills/json_encoder.py

@@ -16,8 +16,7 @@
 class AusBillsJsonEncoder(json.JSONEncoder):
     def default(self, obj):
         if isinstance(obj, Maybe):
-            return {"$nothing": None} if \
-                obj.is_nothing() else {"$just": obj.value}
+            return {"$nothing": None} if obj.is_nothing() else {"$just": obj.value}
         if isinstance(obj, Tag):
             return {"$bs4.tag": obj.encode()}
         if isinstance(obj, bytes):
@@ -28,8 +27,9 @@ def default(self, obj):
             return {"$house": obj.value}
         if isinstance(obj, datetime):
             return {"$dateIso8601": obj.isoformat()}
-        log.warning("Got something of unexpected type"
-                    "({}\n\nObj: {}\n\ndir: {}"
-                    .format(type(obj), str(obj), dir(obj)))
+        log.warning(
+            "Got something of unexpected type"
+            "({}\n\nObj: {}\n\ndir: {}".format(type(obj), str(obj), dir(obj))
+        )
 
         return json_d(self, obj)

ausbills/models.py

@@ -2,8 +2,8 @@
 from typing import Dict, List, NewType
 import json
 
-PdfUrl = NewType('PdfUrl', str)
-UrlStr = NewType('UrlStr', str)
+PdfUrl = NewType("PdfUrl", str)
+UrlStr = NewType("UrlStr", str)
 
 
 @dataclass
@@ -22,7 +22,7 @@ class Bill:
     bill_text_links: List[Dict]
 
     def asDict(self) -> dict:
-        return(self.__dict__)
+        return self.__dict__
 
     def asJson(self) -> str:
-        return(json.dumps(self.asDict(), indent=2))
+        return json.dumps(self.asDict(), indent=2)

ausbills/parliament/act.py

@@ -4,62 +4,79 @@
 
 from ausbills.models import BillMeta, Bill, PdfUrl, UrlStr
 from ausbills.util import BillExtractor, BillListExtractor
-from ausbills.types import BillProgress, Parliament, BillTypes, ChamberProgress, Timestamp
+from ausbills.types import (
+    BillProgress,
+    Parliament,
+    BillTypes,
+    ChamberProgress,
+    Timestamp,
+)
 from ausbills.util.consts import *
 
-BASE_URL = 'https://legislation.act.gov.au'
+BASE_URL = "https://legislation.act.gov.au"
 
 
 class ACTBillList(BillListExtractor):
     def __init__(self):
-        bill_volume = self._download_html(
-            'https://legislation.act.gov.au/results?category=cBil&status=Current&action=browse').find(
-                'table', {'id': 'results-table-bill'}).find('tbody')
+        bill_volume = (
+            self._download_html(
+                "https://legislation.act.gov.au/results?category=cBil&status=Current&action=browse"
+            )
+            .find("table", {"id": "results-table-bill"})
+            .find("tbody")
+        )
         self._bill_list = self._get_bill_list(bill_volume)
 
     def _get_bill_list(self, bill_volume):
         bill_list = []
         has_passed = False
-        for row in bill_volume.find_all('tr', recursive=False):
-            bill_intro_date = row.find('td')['data-order']
-            __title_col = row.find_all('td')[1]
+        for row in bill_volume.find_all("tr", recursive=False):
+            bill_intro_date = row.find("td")["data-order"]
+            __title_col = row.find_all("td")[1]
             bill_title = __title_col.text.strip()
-            bill_url = BASE_URL + __title_col.find('a')['href']
-            bill_intro = self._get_timestamp(bill_intro_date[:8], '%Y%m%d')
+            bill_url = BASE_URL + __title_col.find("a")["href"]
+            bill_intro = self._get_timestamp(bill_intro_date[:8], "%Y%m%d")
 
-            __status_col = row.find_all('td')[-1]
-            if __status_col['data-order'] == 'passed':
+            __status_col = row.find_all("td")[-1]
+            if __status_col["data-order"] == "passed":
                 has_passed = True
-                passed_date = self._get_timestamp(
-                    __status_col.contents[1], '%d %B %Y')
+                passed_date = self._get_timestamp(__status_col.contents[1], "%d %B %Y")
             else:
                 passed_date = None
-            bill_type = self._parse_type(row.find_all('td')[2].text)
+            bill_type = self._parse_type(row.find_all("td")[2].text)
             bill_id = bill_url[-6:-1]
 
             if has_passed:
-                prog_dict = {BillProgress.FIRST.value: True, BillProgress.ASSENTED.value: True}
+                prog_dict = {
+                    BillProgress.FIRST.value: True,
+                    BillProgress.ASSENTED.value: True,
+                }
                 chamber_progress = ChamberProgress.THIRD_READING.value
-            else:        
-                prog_dict = {BillProgress.FIRST.value: True, BillProgress.ASSENTED.value: False} # Bills will always remain in the first house in a unicameral parliament
+            else:
+                prog_dict = {
+                    BillProgress.FIRST.value: True,
+                    BillProgress.ASSENTED.value: False,
+                }  # Bills will always remain in the first house in a unicameral parliament
                 chamber_progress = ChamberProgress.FIRST_READING.value
 
-            bill_list.append({
-                TITLE: bill_title,
-                URL: bill_url,
-                BILL_TYPE: bill_type,
-                INTRO_ASSEMBLY: bill_intro,
-                PASSED_ASSEMBLY: passed_date,
-                PASSED: prog_dict,
-                CHAMBER_PROGRESS: chamber_progress,
-                ID: bill_id,
-            })
+            bill_list.append(
+                {
+                    TITLE: bill_title,
+                    URL: bill_url,
+                    BILL_TYPE: bill_type,
+                    INTRO_ASSEMBLY: bill_intro,
+                    PASSED_ASSEMBLY: passed_date,
+                    PASSED: prog_dict,
+                    CHAMBER_PROGRESS: chamber_progress,
+                    ID: bill_id,
+                }
+            )
         return bill_list
 
     def _parse_type(self, type_string):
-        if type_string == 'GOV':
+        if type_string == "GOV":
             return BillTypes.GOVERNMENT.value
-        elif type_string == 'PMB':
+        elif type_string == "PMB":
             return BillTypes.PRIVATE_MEMBER.value
 
 
@@ -86,76 +103,92 @@ class ACTBillObject(BillExtractor):
 
     def __init__(self, bill_meta: BillMetaACT):
         self.bill_soup = self._download_html(bill_meta.link)
-        self.bill_meta_list = self.bill_soup.find('dl').find_all('dd')
+        self.bill_meta_list = self.bill_soup.find("dl").find_all("dd")
         self.url = bill_meta.link
-        if(len(self.bill_meta_list) is None):
+        if len(self.bill_meta_list) is None:
             raise self.ExtractorError(
-                f'Could not find extra bill metadata:\n\n{self.bill_meta_list}')
+                f"Could not find extra bill metadata:\n\n{self.bill_meta_list}"
+            )
 
     def __str__(self):
         return f"<Bill | URL: '{self.url}'>"
 
     def __repr__(self):
-        return ('<{}.{} : {} object at {}>'.format(
+        return "<{}.{} : {} object at {}>".format(
             self.__class__.__module__,
             self.__class__.__name__,
-            self.url.split('/b/')[-1].replace('/', ''),
-            hex(id(self))))
+            self.url.split("/b/")[-1].replace("/", ""),
+            hex(id(self)),
+        )
 
     def _get_sponsor(self):
         return self.bill_meta_list[1].text.strip()
 
     def _get_text_links(self):
         urls = []
-        table = self.bill_soup.find(
-            'h3', {'tabindex': '0'}).findNext('table').find('tbody')
-        for index, entry in enumerate(table.find_all('tr')):
+        table = (
+            self.bill_soup.find("h3", {"tabindex": "0"}).findNext("table").find("tbody")
+        )
+        for index, entry in enumerate(table.find_all("tr")):
             time = self._get_timestamp(
-                table.find_all('td')[1]['data-order'][:8], '%Y%m%d')
-            url = BASE_URL + entry.find(
-                'a', {'class': 'button download pdf'})['href']
-
-            urls.append({
-                '__time': time,
-                '__id': index,
-                'url': url,
-            })
+                table.find_all("td")[1]["data-order"][:8], "%Y%m%d"
+            )
+            url = BASE_URL + entry.find("a", {"class": "button download pdf"})["href"]
+
+            urls.append(
+                {
+                    "__time": time,
+                    "__id": index,
+                    "url": url,
+                }
+            )
         return urls
 
     def _get_em_links(self):
         urls = []
-        table = self.bill_soup.find(
-            'h3', {'tabindex': None}).findNext('table').find('tbody')
-        for index, row in enumerate(table.find_all('tr')):
+        table = (
+            self.bill_soup.find("h3", {"tabindex": None})
+            .findNext("table")
+            .find("tbody")
+        )
+        for index, row in enumerate(table.find_all("tr")):
             time = self._get_timestamp(
-                table.find_all('td')[1]['data-order'][:8], '%Y%m%d')
-            url = BASE_URL + row.find(
-                'a', {'class': 'button download pdf'})['href']
-            urls.append({
-                '__time': time,
-                '__id': index,
-                'url': url,
-                'house': BillProgress.FIRST.value,
-            })
+                table.find_all("td")[1]["data-order"][:8], "%Y%m%d"
+            )
+            url = BASE_URL + row.find("a", {"class": "button download pdf"})["href"]
+            urls.append(
+                {
+                    "__time": time,
+                    "__id": index,
+                    "url": url,
+                    "house": BillProgress.FIRST.value,
+                }
+            )
         return urls
 
     def _get_scrutiny_link(self):
-        notes_col = self.bill_soup.find(
-            'h3', {'tabindex': '0'}).findNext(
-                'table').find('tbody').find('td', {'class': 'notes'})
-        if(notes_col is not None):
-            for a in notes_col.find_all('a'):
-                if(a.contents[0] == 'Scrutiny Committee report'):
-                    return a['href']
+        notes_col = (
+            self.bill_soup.find("h3", {"tabindex": "0"})
+            .findNext("table")
+            .find("tbody")
+            .find("td", {"class": "notes"})
+        )
+        if notes_col is not None:
+            for a in notes_col.find_all("a"):
+                if a.contents[0] == "Scrutiny Committee report":
+                    return a["href"]
 
     def _get_speech_link(self):
-        notes_col = self.bill_soup.find(
-            'h3', {'tabindex': '0'}).findNext(
-                'table').find('tbody').find('td', {'class': 'notes'})
-        if(notes_col is not None):
-            for a in notes_col.find_all('a'):
-                if(a.contents[0] == 'Presentation speech'):
-                    return a['href']
+        notes_col = (
+            self.bill_soup.find("h3", {"tabindex": "0"})
+            .findNext("table")
+            .find("tbody")
+            .find("td", {"class": "notes"})
+        )
+        if notes_col is not None:
+            for a in notes_col.find_all("a"):
+                if a.contents[0] == "Presentation speech":
+                    return a["href"]
 
 
 def get_bills_metadata() -> List[BillMetaACT]:
@@ -171,20 +204,22 @@ def get_bills_metadata() -> List[BillMetaACT]:
             passed_assembly=bill_dict[PASSED_ASSEMBLY],
             intro_assembly=bill_dict[INTRO_ASSEMBLY],
             id=bill_dict[ID],
-            chamber_progress=bill_dict[CHAMBER_PROGRESS]
+            chamber_progress=bill_dict[CHAMBER_PROGRESS],
         )
         _bill_meta_list.append(bill_meta)
-    return(_bill_meta_list)
+    return _bill_meta_list
 
 
 def get_bill(bill_meta: BillMetaACT) -> BillACT:
     act_helper = ACTBillObject(bill_meta)
     bill_act = BillACT(
-        **dataclasses.asdict(bill_meta),  # Copy metadata we already got as separate instance.
+        **dataclasses.asdict(
+            bill_meta
+        ),  # Copy metadata we already got as separate instance.
         sponsor=act_helper._get_sponsor(),
         bill_text_links=act_helper._get_text_links(),
         bill_em_links=act_helper._get_em_links(),
         intro_speech=act_helper._get_speech_link(),
-        scrutiny_report=act_helper._get_scrutiny_link()
+        scrutiny_report=act_helper._get_scrutiny_link(),
     )
     return bill_act