diff options
Diffstat (limited to 'parser/scrapeToJson.py')
| -rwxr-xr-x | parser/scrapeToJson.py | 34 |
1 files changed, 17 insertions, 17 deletions
diff --git a/parser/scrapeToJson.py b/parser/scrapeToJson.py index 5eacb5a..cbe9999 100755 --- a/parser/scrapeToJson.py +++ b/parser/scrapeToJson.py @@ -13,7 +13,7 @@ def processMonster(data, weapons, armors, spells): desc = Creature() desc['entry'] = 'creatures' for name in names2names: - m = re.search('(\*\*{}\.?\*\*)(.*)'.format(names2names[name]), data) + m = re.search(r'(\*\*{}\.?\*\*)(.*)'.format(names2names[name]), data) if m: desc[name] = m.group(2).strip() else: @@ -33,23 +33,23 @@ def processMonster(data, weapons, armors, spells): if 'nonmagical' in part: qualifiers.append('nonmagical') if 'that aren\'t' in part: - qualifiers.append('non-' + re.search('(?<=that aren\'t ).*$', part).group(0)) + qualifiers.append('non-' + re.search(r"(?<=that aren't ).*$", part).group(0)) if 'not made with ' in part: - qualifiers.append('non-' + re.search('(?<=not made with )\w*', part).group(0)) - for typ in re.findall('([a-z]+(?=,)|^[a-z]+$|(?<=, )[a-z]+$|(?<=and )[a-z]+(?= from)|(?<=and )[a-z]+(?= \(from))', part): + qualifiers.append('non-' + re.search(r'(?<=not made with )\w*', part).group(0)) + for typ in re.findall(r'([a-z]+(?=,)|^[a-z]+$|(?<=, )[a-z]+$|(?<=and )[a-z]+(?= from)|(?<=and )[a-z]+(?= \(from))', part): desc[name].append({'type': typ, 'qualifiers': qualifiers}) # Calc things about hp - hitdieMatch = re.search('(\d+)d(\d+)', desc['hp']) + hitdieMatch = re.search(r'(\d+)d(\d+)', desc['hp']) desc['hit_die_count'] = int(hitdieMatch.group(1)) desc['hit_die_sides'] = int(hitdieMatch.group(2)) del desc['hp'] - desc['name'] = re.search('(?<=name: ).*', data).group(0).strip() - desc['type'] = re.search('(?<=type: ).*', data).group(0).strip() + desc['name'] = re.search(r'(?<=name: ).*', data).group(0).strip() + desc['type'] = re.search(r'(?<=type: ).*', data).group(0).strip() desc['cr'] = float(re.search('(?<=cr: ).*', data).group(0).strip()) - description = re.search('(?<=_).*(?=_)', data).group(0).strip() + description = re.search(r'(?<=_).*(?=_)', data).group(0).strip() desc['size'] = description.split(' ')[0] desc['alignment'] = description.split(', ')[-1] - desc['stats'] = {ability: int(score.strip().split(' ')[0]) for ability, score in zip(['str', 'dex', 'con', 'int', 'wis', 'cha'], re.findall('(?<=\|) *\d.*?(?=\|)', data))} + desc['stats'] = {ability: int(score.strip().split(' ')[0]) for ability, score in zip(['str', 'dex', 'con', 'int', 'wis', 'cha'], re.findall(r'(?<=\|) *\d.*?(?=\|)', data))} desc['inventory'] = [] # Fill with weapons and armor desc['observant'] = False # maybe set to true later # Add a few null-valued items that will be set when the creature is first generated @@ -61,7 +61,7 @@ def processMonster(data, weapons, armors, spells): correctAC = int(desc['ac'].split(' ')[0] if ' ' in desc['ac'] else desc['ac']) natural = '' armorBonus = 0 - armor = re.search('(?<=\().*(?=\))', desc['ac']) + armor = re.search(r'(?<=\().*(?=\))', desc['ac']) if armor: armor = armor.group(0).lower() if ',' in armor: @@ -71,7 +71,7 @@ def processMonster(data, weapons, armors, spells): for a in armor: a = a.strip() # If it has "armor" in it, remove that - a = re.search('^(.*?)(?: armor)?$', a).group(1) + a = re.search(r'^(.*?)(?: armor)?$', a).group(1) #print('Working with {}'.format(a)) if a == 'natural' or a == 'patchwork' or 'scraps' in a: natural = a @@ -111,28 +111,28 @@ def processMonster(data, weapons, armors, spells): # Search for a description section desc['text'] = '' - description = re.search('(?s)(?<={}).*?(?=###|$)'.format('### Description'), data) + description = re.search(r'(?s)(?<={}).*?(?=###|$)'.format('### Description'), data) if description: desc['text'] = description.group(0).strip() else: # Try looking for the last entry (**something**) with an empty line and then one or more paragraphs before end of file - description = re.search('(?s)(?<=\*\*).*\n\n(.*?)(?=###|$)', data) + description = re.search(r'(?s)(?<=\*\*).*\n\n(.*?)(?=###|$)', data) if description: #print(f'Found description without a header for {desc["name"]}') desc['text'] = description.group(1).strip() # Next do sections - names2sectHeads = {'feature': '\*\*Challenge\*\*', 'action': '### Actions', 'legendary_action': '### Legendary Actions', 'reaction': '### Reactions'} + names2sectHeads = {'feature': r'\*\*Challenge\*\*', 'action': '### Actions', 'legendary_action': '### Legendary Actions', 'reaction': '### Reactions'} # We put them all in "features" list desc['features'] = [] for name in names2sectHeads: - section = re.search('(?s)(?<={}).*?(?=###|$)'.format(names2sectHeads[name]), data) + section = re.search(r'(?s)(?<={}).*?(?=###|$)'.format(names2sectHeads[name]), data) if section: # There might be a special section text as the first new line after the header #text = re.match('(?s)(\s*\w[^\*].*?)([\r\n]+[\*#]|$)', '\n'.join(section.group(0).split('\n')[1:])) #if text and re.search('\w', text.group(1)): # desc[name]['_text'] = text.group(1).strip() - for m in re.findall('(?s)\n\*\*(.*?)\.?\*\*(.*?)(?=\n\*\*|\n\n|$)', section.group(0)): + for m in re.findall(r'(?s)\n\*\*(.*?)\.?\*\*(.*?)(?=\n\*\*|\n\n|$)', section.group(0)): desc['features'].append({'entry': 'feature', 'name': m[0].lower(), 'text': m[1].strip(), 'type': name}) # Next, simplify and codify a few things # Guess the proficiency bonus @@ -157,7 +157,7 @@ def processMonster(data, weapons, armors, spells): print('Things came out funny for {}; {} save has bonus {}, but proficiency is {} and the relevant ability ({}) gets {}'.format(desc['name'], ability, int(save.split('+')[1]), desc['prof'], ability, desc.getBonus(ability))) desc['saves'].append(ability) for action in desc['features']: - if re.match('.*Attack:', action['text']): + if re.match(r'.*Attack:', action['text']): attacks.procAttackAction(desc, action, weapons) elif 'spellcasting' in action['name']: attacks.procSpellAction(desc, action, spells) |