xevion/the-office
1
0
Fork 0
mirror of https://github.com/Xevion/the-office.git synced 2025-12-10 02:08:48 -06:00
Code Issues Packages Projects Releases Wiki Activity

fix assert, fix quote patern, fix Section builder with deleted scene handling, added clearing methods, added Section repr

Browse Source
This commit is contained in:
Xevion
2020-01-20 06:08:16 -06:00
parent 9c00745503
commit 94099c364d
1 changed files with 29 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
app/models.py
View File

@@ -5,14 +5,14 @@ from bs4 import BeautifulSoup
from app import db, login
episodes = [5, 6, 22, 23, 14, 26, 24, 24, 24, 23]
quotePattern = r'(\w+):.+'
quotePattern = r'([\w\s]+):(.+)'
class Season(db.Model):
id = db.Column(db.Integer, primary_key=True)
episodes = db.relationship('Episode', backref='season', lazy='dynamic')
def __init__(self, **kwargs):
assert 0 >= kwargs.get('id') <= 9, "Season ID must be 0-9 inclusive"
assert 0 <= kwargs.get('id') <= 9, "Season ID must be 0-9 inclusive"
super(Season, self).__init__(**kwargs)
def build(self):
@@ -50,20 +50,30 @@ class Episode(db.Model):
def build(self):
"""downloads, processes, and automatically creates Sections and Quotes"""
link = f'http://officequotes.net/no{self.season_id}-{str(self.episode).zfill(2)}.php'
link = f'http://officequotes.net/no{self.season_id}-{str(self.number).zfill(2)}.php'
data = requests.get(link).text
soup = BeautifulSoup(data, 'html.parser')
sections = soup.find_all(attrs={'class' : 'quote'})
deleted = 0
for section in sections:
quotes = [quote.string + quote.next_sibling.string for quote in section.find_all('b')]
isDeletedScene = quotes[0].lower().startswith('deleted scene')
if isDeletedScene: deleted += 1
s = Section(episode=self, deleted=deleted if isDeletedScene else -1, quotes=quotes)
if isDeletedScene:
deleted += 1
s = Section(episode_id=self.id, deleted=deleted if isDeletedScene else -1)
s.build(quotes[1:] if isDeletedScene else quotes)
db.session.add(s)
db.session.commit()
def clear(self):
sections = Section.query.filter_by(episode_id=self.id).all()
print(f'Clearing {len(sections)} from Databse for Episode {self.number} of Season {self.season_id}')
for section in sections:
section.clear(commit=False)
db.session.commit()
@property
def scrapeURL(self):
return f'http://officequotes.net/no{self.season_id}-{str(self.number).zfill(2)}.php'
@@ -75,17 +85,29 @@ class Section(db.Model):
deleted = db.Column(db.Integer, default=-1)
quotes = db.relationship('Quote', backref='section', lazy='dynamic')
def build(self, quotes, commit=False):
def build(self, quotes, commit=False, reset=False):
"""given an List of unformatted script quotes, automatically creates Quotes assigned to this Section"""
for quote in quotes:
if quote.lower().startswith('deleted scene'):
raise Exception(f'Deleted Scene Quote passed to Section Builder: "{quote}"')
match = re.match(quotePattern, quote)
assert match != None, f"Quote '{quote}' could not be processed."
q = Quote(section=self, speaker=match[1], text=match[2])
q = Quote(section=self, speaker=match[1].strip(), text=match[2].strip())
db.session.add(q)
if commit: db.session.commit()
def clear(self, commit=True):
quotes = Quote.query.filter_by(section_id=self.id).all()
print(f'Clearing {len(quotes)} quotes from Section ID {self.id}')
for quote in quotes:
db.session.delete(quote)
if commit: db.session.commit()
def __repr__(self):
season = Episode.query.get(self.episode_id).first().id
quotes = len(Quote.query.filter_by(section_id=self.id).all())
return f'Section(id={self.id} episode={self.episode_id} season={season} quotes=[{quotes}...])'
class Quote(db.Model):
"""represents a specific quote by a specific speaker"""
id = db.Column(db.Integer, primary_key=True)