more docs, if/elif fixed, more functions in utils

crawl.py

@@ -5,7 +5,6 @@ import argparse
 import sys
 import os
 import pathlib
-
 from datetime import date as DTDate
 from datetime import datetime as DTDateTime
 import appdirs
@@ -77,7 +76,7 @@ AMOUNT CURRENCY: Convert AMOUNT euros to CURRENCY.
 CURRENCY AMOUNT: Convert AMOUNT CURRENCY to euros.
 d | date: Print the date which the data is from.
             """)
-        if argv[0] in ['q', 'exit', 'quit']:
+        elif argv[0] in ['q', 'exit', 'quit']:
             sys.exit()
         elif argv[0] in ['date', 'd']:
             print(res.date)
@@ -166,7 +165,7 @@ else:
     filepath = pathlib.Path(appdirs.user_cache_dir('FirstDataCrawler', 'iwonder'))
 if not filepath.exists():
     filepath.mkdir(parents=True)
-filename = filepath / (retrieve_date.strftime('%Y%m%d') + '.pdf')
+filename = filepath / utils.mk_filename(retrieve_date, use_card_type)
 if os.path.exists(filename):
     with open(filename, 'rb') as f:
         results = utils.get_results_from_pdf(f)

utils.py

@@ -29,6 +29,7 @@ def _parse_rate(text: str) -> float or None:
     if re.match('Keine Kursdaten vorhanden', text):
         _r = None
     else:
+        # strip whitespace and format decimal numbers correctly for parsing
         text = text.strip(' ').replace(',', '.')
         try:
             _r = float(text)
@@ -37,15 +38,18 @@ def _parse_rate(text: str) -> float or None:
     return _r
 
 def _parse_card_type(text: str) -> str:
+    # Method for validating metadata from the PDF against the request data
     text = text.split(':')[1]
     text = text.strip('" ')
     return text
 
 def _parse_date(text: str) -> DTDate:
+    # Method for validating metadata from the PDF against the request data
     text = text.split(': ')[1].rstrip()
     return DTDateTime.strptime(text, '%d.%m.%Y').date()
 
 def _array_remove_empty(obj: list) -> List[str]:
+    # just a macro for removing empty or empty-string array objects
     try:
         while True:
             obj.remove('')
@@ -119,21 +123,35 @@ def get_fileio(date: DTDate, card_type: List[str] = CARD_VISA) -> BinaryIO: # py
     # b.set_debug_responses(True)
     # PDF URL
     b.open('https://misc.firstdata.eu/CurrencyCalculator/fremdwaehrungskurse/pdf')
-    fm = b.forms()
+    fm = b.forms()[0]
-    fm_i = fm[0]
+    # This must be done because I can't change the options otherwise
-    fm_i.set_all_readonly(False)
+    fm.set_all_readonly(False)
     # Configure form
-    fm_i['creditCardsRadio'] = card_type # VISA
+    fm['creditCardsRadio'] = card_type
-    fm_i['selectedDatesString'] = str(date.strftime('%Y%m%d') + ',')
+    fm['selectedDatesString'] = str(date.strftime('%Y%m%d') + ',')
-    # Retrieve file using button click
+    # Retrieve file using button click; the button is 115x21 pixels in size.
-    rq = fm_i.click(name='submitButton', coord=(random.randint(1, 119), random.randint(1, 20)))
+    # The API apparently doesn't like the max values
+    rq = fm.click(name='submitButton', coord=(random.randint(1, 114), random.randint(1, 20)))
     rq.add_header('Accept', '*/*')
     rp = b.retrieve(rq)
     print(' Done.')
+    # Returns an open file-like object with the PDF as contents
     return open(rp[0], 'rb')
 def get_date() -> DTDate:
+    # For Sunday and Monday, use Friday's data; Saturday and Sunday are completely null
     if DTDate.today().weekday() in [6, 0]:
         date = DTDate.today() + relativedelta(weekday=FR(-1))
     else:
+    # For all other days, the previous day is fine
         date = DTDate.today() - DTTimeDelta(1)
     return date
+
+def mk_filename(date: DTDate, card_type: List[str]) -> str:
+    # List[str] is used because I don't want to make a class for just this
+    if card_type == CARD_MASTERCARD:
+        fn = date.isoformat() + '_MC.pdf'
+    elif card_type == CARD_VISA:
+        fn = date.isoformat() + '_VISA.pdf'
+    else:
+        raise TypeError("not a valid card type")
+    return fn