def parse_person():
data = {}
for person in models.Person.query.all(): #.filter_by(name_original=None)
while True:
try:
r = ProxyRequests(f'{URL}{person.links}')
except:
break
r.get()
r.encoding = 'utf-8'
text = r.request
soup = BeautifulSoup(text, 'html.parser')
if not soup.find('h1', {'itemprop': 'name'}):
continue
alternateName = soup.find('span', {'itemprop': 'alternateName'})
if alternateName:
person.name_original = alternateName.text
else:
person.name_original = person.name
db.session.add(person)
db.session.commit()
list_career = []
director = soup.find('a', {'href': '#director'})
if director:
egge = director.text.replace(' ', '')
if not models.Career.query.filter_by(name=egge).first():
new_career = models.Career(name=egge)
db.session.add(new_career)
db.session.commit()
list_career.append(new_career)
else:
list_career.append(
models.Career.query.filter_by(name=egge).first())
actor = soup.find('a', {'href': '#actor'})
if actor:
egge = actor.text.replace(' ', '')
if not models.Career.query.filter_by(name=egge).first():
new_career = models.Career(name=egge)
db.session.add(new_career)
db.session.commit()
list_career.append(new_career)
else:
list_career.append(
models.Career.query.filter_by(name=egge).first())
person.career.clear()
for i in list_career:
person.career.append(i)
db.session.add(person)
db.session.commit()
break
def parse_links():
page = 1
last_page = 1
data = {}
while page <= last_page:
r = ProxyRequests(f'{URL}/top/navigator/m_act[rating]/1%3A/order/rating/page/{page}/#results')
r.get()
r.encoding = 'utf-8'
text = r.request
soup = BeautifulSoup(text)
if last_page == 1:
try:
last_link = soup.find_all('li', {'class': 'arr'})[-1].find('a').get('href')
last_page = int(re.findall(r'\d{2,}', last_link)[0])
except:
continue
movie_link = soup.find_all('div', {'class': '_NO_HIGHLIGHT_'})
if not movie_link:
continue
for i in movie_link:
i_soup = BeautifulSoup(f'b{i}').find('div', {'class': 'name'}).find('a')
i_text = i_soup.text
i_link = i_soup.get('href')
id_film = int(re.findall(r'\d{1,}', i_link)[1])
if models.Film.query.filter_by(id_film=id_film).first() == None:
film = models.Film(id_film=id_film, links=i_link, name=i_text)
db.session.add(film)
try:
db.session.commit()
except Exception:
db.session.rollback()
data[i_text] = {page:i_link}
continue
page += 1
with open('data.txt', 'w', encoding='utf-8') as f:
json.dump(data, f, ensure_ascii=False)
def parse_films():
engine = create_engine('sqlite:///:memory:', echo=True)
data = {}
for film in models.Film.query.filter_by(rating_kp=None).all(): #
while True:
try:
r = ProxyRequests(f'{URL}{film.links}')
except:
break
r.get()
r.encoding = 'utf-8'
text = r.request
soup = BeautifulSoup(text, 'html.parser')
genres = soup.find('span', {'itemprop': 'genre'})
if genres:
genres = genres.find_all('a')
countrys = soup.find_all(
'div', {'style': 'position: relative'})[1].find_all('a')
persons = soup.find_all('li', {'itemprop': 'actors'})
for director in soup.find_all('td', {'itemprop': 'director'}):
persons.append(director)
break
list_genres = []
for genre in genres:
if not models.Genre.query.filter_by(name=genre.text).first():
while True:
new_genre = models.Genre(name=genre.text)
db.session.add(new_genre)
try:
db.session.commit()
list_genres.append(new_genre)
break
except Exception:
db.session.rollback()
else:
list_genres.append(
models.Genre.query.filter_by(name=genre.text).first())
list_countrys = []
for country in countrys:
if not models.Country.query.filter_by(name=country.text).first():
while True:
new_country = models.Country(name=country.text)
db.session.add(new_country)
try:
db.session.commit()
list_countrys.append(new_country)
break
except Exception:
db.session.rollback()
else:
list_countrys.append(
models.Country.query.filter_by(name=country.text).first())
list_person = []
for person in persons:
if person.find('a').text.replace(' ', '') == '...':
break
person_link = person.find('a').get('href')
if not models.Person.query.filter_by(id_person_kp=int(
re.findall(r'\d{1,}', person_link)[0])).first():
while True:
# person_link = person.find('a').get('href')
if models.Person.query.filter_by(id_person_kp=int(
re.findall(r'\d{1,}', person_link)[0])).first():
break
id_person_kp = int(re.findall(r'\d{1,}', person_link)[0])
new_person = models.Person(name=person.text,
links=person_link,
id_person_kp=id_person_kp)
db.session.add(new_person)
try:
db.session.commit()
list_person.append(new_person)
break
except Exception:
db.session.rollback()
else:
if not models.Person.query.filter_by(id_person_kp=int(
re.findall(r'\d{1,}', person_link)
[0])).first() in list_person:
list_person.append(
models.Person.query.filter_by(id_person_kp=int(
re.findall(r'\d{1,}', person_link)[0])).first())
# if not film.description:
while True:
try:
film.name = soup.find('span', {
'class': 'moviename-title-wrapper'
}).text
film.name_original = film.name if not soup.find(
'span', {
'class': 'alternativeHeadline'
}).text else soup.find('span', {
'class': 'alternativeHeadline'
}).text
film.description = soup.find('div', {
'itemprop': 'description'
}).text.replace(chr(151), '-')
film.rating_kp = float(
soup.find('span', {
'class': 'rating_ball'
}).text)
film.rating_imdb = float(
re.findall(
r'[\d][^ ]+',
soup.find('div', {
'style':
'color:#999;font:100 11px tahoma, verdana'
}).text)[0])
film.date_released = int(
soup.find('div', {
'style': 'position: relative'
}).find('a').text)
try:
db.session.commit()
except Exception:
db.session.rollback()
continue
film.genre.clear()
film.country.clear()
film.person.clear()
while True:
for i in list_genres:
film.genre.append(i)
for i in list_countrys:
film.country.append(i)
for i in list_person:
film.person.append(i)
db.session.add(film)
try:
db.session.commit()
break
except Exception:
db.session.rollback()
break
except:
db.session.rollback()
