def __init__(self, title_id):
self.title_id = title_id
self.ratings_uri = imdb_uris["criticreviews"] % self.title_id
soup = BeautifulSoup(get(self.ratings_uri).text, 'lxml')
"""
:returns: Holds page Info tags
"""
critic_tag = catch('None',
lambda: soup.select('tr[itemprop="reviews"]'))
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
"""
:returns: Movie Title
"""
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
:returns: Critic Review Demographics
"""
self.critic_reviews_df = catch('None', lambda: critic_df(critic_tag))
def __init__(self, title_id):
self.title_id = title_id
self.ratings_uri = imdb_uris["ratings"] % self.title_id
soup = BeautifulSoup(get(self.ratings_uri).text, 'lxml')
"""
:returns: Holds page Info tags
"""
rating_demo_tag = catch(
'None', lambda: soup.find('div', string=tag_search['rating_demo']).
findNext('table'))
"""
:returns: Movie Title
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
:returns: Rating Demographics
"""
self.rating_df = catch('None', lambda: rating_df(rating_demo_tag))
self.rating_demo_df = catch('None',
lambda: rating_demo_df(rating_demo_tag))
self.rating_demo_us_df = catch(
'None', lambda: rating_demo_region_df(rating_demo_tag))
self.rating_math = catch(
'dict', lambda: {
'Arithmetic Mean':
rating_demo_tag.findPrevious('table').findNextSibling(
'div', class_="allText").get_text().split()[3],
'Median':
rating_demo_tag.findPrevious('table').findNextSibling(
'div', class_="allText").get_text().split()[-1]
})
"""
:returns: Rating
"""
self.votes = catch(
'None', lambda: digits(soup.select_one('.allText').contents[0]))
self.rating = catch(
'None', lambda: float(
soup.select_one('.allText').contents[2].split()[2:][0]))
def __init__(self, title_id):
self.title_id = title_id
self.plot_uri = imdb_uris["plotsummary"] % self.title_id
soup = BeautifulSoup(get(self.plot_uri).text, 'lxml')
"""
:returns: Movie Title
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
:returns: Movie Plot
"""
self.plot = catch(
'None', lambda: unicode(
soup.select_one('#synopsis').findNext('ul').get_text()).
replace("\'", ""))
"""
:returns: Movies Summaries
"""
block = catch(
'None',
lambda: soup.select_one('#summaries').findNext('ul').select('li'))
self.summaries = catch(
'None',
lambda: [unicode(' '.join(tag.text.split())) for tag in block])
"""
:returns: Creates Dict from the above info. if available.
"""
self.imdb_plot_metadata = catch(
'dict', lambda: {
"Movie Name": self.title,
"Movie URI": self.title_url,
"Title ID": self.title_id,
"Year": self.year,
"Movie Plot URI": self.plot_uri,
"Plot": self.plot,
"Summaries": self.summaries
})
def __init__(self, text: str) -> bool:
self.entered_text = text
self.url = search_imdb_id["character"] % ''.join(
self.entered_text.split())
soup = BeautifulSoup(get(self.url).text, 'lxml')
suggestions, names, imdbids = [], [], []
name = soup.select('.result_text')
try:
if len(name) > 20:
for item in name[:20]:
print('%s: %s' %
((name.index(item) + 1), unicode(item.get_text())))
suggestions.append(item.a['href'][7:16])
names.append(item.a.text.strip())
else:
for item in name:
print('%s: %s' %
((name.index(item) + 1), unicode(item.get_text())))
suggestions.append(item.a['href'][7:16])
names.append(item.a.text.strip())
input_name = re.findall(r"[\w']+", input('Enter serial number\t'))
imdbids = [
suggestions[int(load) - 1] if int(load) != 0 else ''
for load in input_name
]
names = [
names[int(load) - 1] if int(load) != 0 else ''
for load in input_name
]
if len(imdbids) == 1:
self.character_name = names[0]
self.character_id = imdbids[0]
else:
self.character_name = names
self.character_id = imdbids
except Exception as es:
print("{0} :".format(type(es)), es)
sys.exit(0)
def __init__(self, title_id: str) -> bool:
self.title_id = title_id
self.taglines_uri = imdb_uris["taglines"] % self.title_id
soup = BeautifulSoup(get(self.taglines_uri).text, 'lxml')
"""
:returns: Movie Title
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
:returns: Holds page Info tags
"""
taglines_tag = catch(
'None',
lambda: soup.select_one('#taglines_content').select('.soda'))
"""
returns: taglines if available
"""
self.taglines = catch(
'list',
lambda: [unicode(tagline.get_text()) for tagline in taglines_tag])
"""
:returns: Creates Dict from the above info. if available.
"""
self.imdb_taglines_metadata = catch(
'dict', lambda: {
"Movie Name": self.title,
"Movie URI": self.title_url,
"Title ID": self.title_id,
"Year": self.year,
"Movie Taglines URI": self.taglines_uri,
"Taglines": self.taglines
})
def __init__(self, title_id):
self.title_id = title_id
self.plot_keywords_url = imdb_uris["keywords"] % self.title_id
soup = BeautifulSoup(get(self.plot_keywords_url).text, 'lxml')
"""
:returns: Movie Title
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
:returns: Movie Plot Keywords
"""
block = catch('None', lambda: soup.select('td.soda'))
self.plot_keywords = catch(
'list', lambda: [tag['data-item-keyword'] for tag in block])
"""
:returns: Creates Dict from the above info. if available.
"""
self.imdb_plot_Keywords_metadata = catch(
'dict', lambda: {
"Movie Name": self.title,
"Movie URI": self.title_url,
"Title ID": self.title_id,
"Year": self.year,
"Movie Plot Keywords URL": self.plot_keywords_url,
"Plot Keywords": self.plot_keywords
})
def __init__(self, title_id):
self.title_id = title_id
self.release_info_url = imdb_uris["releaseinfo"] % self.title_id
soup = BeautifulSoup(get(self.release_info_url).text, 'lxml')
"""
:returns: table tag index
"""
table_tag = catch('None', lambda: soup.select('h4'))
"""
:returns: Movie Title
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
returns: tags
"""
releases = catch(
'None', lambda: table_tag[index_finder(table_tag, 'release')].
findNext('table').select('tr'))
"""
returns: Release Info DataFrame if available.
"""
try:
self.releases_df = pd.DataFrame(
columns=['Country', 'URI', 'Date', 'Location'])
for tag in releases:
self.releases_df.loc[len(self.releases_df)] = [
catch(
'None', lambda: unicode(
tag.select_one('td.release-date-item__country-name'
).a.get_text())),
catch(
'None', lambda: "%s%s" %
(base_uri,
unicode(
tag.select_one(
'td.release-date-item__country-name').a[
'href'][1:]))),
catch(
'None', lambda: unicode(
tag.select_one('td.release-date-item__date').
get_text())),
catch(
'None', lambda: unicode(
tag.select_one('td.release-date-item__attributes').
get_text()))
]
self.releases_df = dataframe_data(self.releases_df)
except:
self.releases_df = None
"""
:returns: Released Countries, Dates, Location list if available.
"""
self.released_country_names = catch(
'list', lambda: self.releases_df.Country.tolist())
self.released_country_uri = catch(
'list', lambda: self.releases_df.URI.tolist())
self.released_dates = catch('list',
lambda: self.releases_df.Date.tolist())
self.released_locations = catch(
'list', lambda: self.releases_df.Location.tolist())
"""
:returns: Released Date in India if available.
"""
self.release_date_in_india = catch(
'None',
lambda: unicode(releases[india_index_finder(releases, 'india')].
select_one('td').findNext('td').get_text()))
"""
returns: Also Known As DataFrame if available.
"""
try:
aka = table_tag[index_finder(
table_tag, 'also known as')].findNext('table').select('tr')
self.also_known_as_df = pd.DataFrame(columns=['Country', 'Title'])
for tag in aka:
self.also_known_as_df.loc[len(self.also_known_as_df)] = [
catch(
'None', lambda: unicode(
tag.select_one('td.aka-item__name').get_text())),
catch(
'None', lambda: unicode(
tag.select_one('td.aka-item__title').get_text()))
]
self.also_known_as_df = dataframe_data(self.also_known_as_df)
except:
self.also_known_as_df = None
"""
:returns: Also Known As Countries, Title list if available.
"""
self.also_known_as_country_names = catch(
'list', lambda: self.also_known_as_df.Country.tolist())
self.also_known_as_titles = catch(
'list', lambda: self.also_known_as_df.Title.tolist())
"""
:returns: Creates Meta Data from the above info. if available.
"""
self.imdb_release_info_metadata = catch(
'dict', lambda: {
"Movie Name": self.title,
"Movie URI": self.title_url,
"Title ID": self.title_id,
"Year": self.year,
"Movie Release Info URL": self.release_info_url,
"India Release Date": self.release_date_in_india,
"Release Dates": {
"Country": self.released_country_names,
"URI": self.released_country_uri,
"Date": self.released_dates,
"Location": self.released_locations
},
"Also Known As (AKA)": {
"Country": self.also_known_as_country_names,
"Title": self.also_known_as_titles
}
})
def __init__(self, title_id):
self.title_id = title_id
self.technical_spec_url = imdb_uris["technical"] % self.title_id
soup = BeautifulSoup(get(self.technical_spec_url).text, 'lxml')
"""
:returns: Holds page Info tags
"""
technical_spec_tag = catch(
'None', lambda: soup.select('td[class="label"]'))
movie_tag = catch(
'None', lambda: soup.select_one('h3[itemprop="name"]'))
"""
:returns: Movie Title
"""
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch('None', lambda: unicode(
'%s%s' % (base_uri, movie_tag.a['href'][1:])))
self.year = catch('None', lambda: int(re.findall(
r"\d+", unicode(movie_tag.select_one('.nobr').get_text()))[0]))
"""
:returns: movie runtime if available.
"""
self.runtime = catch('None', lambda: unicode(technical_spec_tag[index_finder(
technical_spec_tag, tag_search['runtime'])].findNext('td').text))
"""
:returns: movie sound mix if available.
"""
sound_mix = catch('None', lambda: technical_spec_tag[index_finder(
technical_spec_tag, tag_search['sound mix'])].findNext('td').select('a'))
self.sound_mix_df = catch('None', lambda: technical_specs(sound_mix))
self.sound_mix_name = catch(
'list', lambda: self.sound_mix_df.Name.tolist())
self.sound_mix_uri = catch(
'list', lambda: self.sound_mix_df.URI.tolist())
"""
:returns: movie color if available.
"""
color = catch('None', lambda: technical_spec_tag[index_finder(
technical_spec_tag, tag_search['color'])].findNext('td').select('a'))
self.color_df = catch('None', lambda: technical_specs(color))
self.color_name = catch('list', lambda: self.color_df.Name.tolist())
self.color_uri = catch('list', lambda: self.color_df.URI.tolist())
"""
:returns: movie aspect ratio if available.
"""
aspect_ratio = catch('list', lambda: list(technical_spec_tag[index_finder(
technical_spec_tag, 'aspect ratio')].findNext('td').stripped_strings))
self.aspect_ratio = catch('list', lambda: [unicode(
' '.join(item.split())) for item in aspect_ratio])
"""
:returns: movie camera if available.
"""
camera = catch('list', lambda: list(technical_spec_tag[index_finder(
technical_spec_tag, 'camera')].findNext('td').stripped_strings))
self.camera = catch('list', lambda: [unicode(
' '.join(item.split())) for item in camera])
"""
:returns: movie laboratory if available.
"""
laboratory = catch('list', lambda: list(technical_spec_tag[index_finder(
technical_spec_tag, 'laboratory')].findNext('td').stripped_strings))
self.laboratory = catch('list', lambda: [unicode(
' '.join(item.split())) for item in laboratory])
"""
:returns: negative format if available.
"""
self.negative_format = catch('list', lambda: unicode(' '.join(technical_spec_tag[index_finder(
technical_spec_tag, 'negative format')].findNext('td').get_text().split())))
"""
:returns: cinematography process if available.
"""
cinematographic_process = catch('list', lambda: list(technical_spec_tag[index_finder(
technical_spec_tag, 'cinematographic process')].findNext('td').stripped_strings))
self.cinematographic_process = catch('list', lambda: [unicode(
' '.join(item.split())) for item in cinematographic_process])
"""
:returns: printed film format if available.
"""
printed_film_format = catch('list', lambda: list(technical_spec_tag[index_finder(
technical_spec_tag, 'printed film format')].findNext('td').stripped_strings))
self.printed_film_format = catch('list', lambda: [unicode(
' '.join(item.split())) for item in printed_film_format])
"""
:returns: film length if available.
"""
film_length = catch('list', lambda: list(technical_spec_tag[index_finder(
technical_spec_tag, 'film length')].findNext('td').stripped_strings))
self.film_length = catch('list', lambda: [unicode(
' '.join(item.split())) for item in film_length])
"""
:returns: Creates Dict from the above info. if available.
"""
self.imdb_technical_spec_metadata = catch('dict', lambda: {"Movie Name": self.title,
"Movie URI": self.title_url,
"Title ID": self.title_id,
"Year": self.year,
"Movie Technical Spec URL": self.technical_spec_url,
"Runtime": self.runtime,
"Sound Mix": {"Name": self.sound_mix_name,
"URI": self.sound_mix_uri},
"Color": {"Name": self.color_name,
"URI": self.color_uri},
"Aspect Ratio": self.aspect_ratio,
"Camera": self.camera,
"Laboratory": self.laboratory,
"Negative Film Format": self.negative_format,
"Cinematography Process": self.cinematographic_process,
"Printed Film Format": self.printed_film_format,
"Film Length": self.film_length})
def __init__(self, title_id):
self.title_id = title_id
self.external_sites_url = imdb_uris["externalsites"] % self.title_id
soup = BeautifulSoup(get(self.external_sites_url).text, 'lxml')
"""
:returns: Movie Title
"""
movie_tag = catch(
'None', lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch('None', lambda: unicode(
'%s%s' % (base_uri, movie_tag.a['href'][1:])))
self.year = catch('None', lambda: int(re.findall(
r"\d+", unicode(movie_tag.select_one('.nobr').get_text()))[0]))
"""
returns: Official Sites DataFrame if available.
"""
self.official_sites_df = catch(
'None', lambda: external_site(tag_search['official'], soup))
self.official_sites_names = catch(
'list', lambda: self.official_sites_df.Name.tolist())
self.official_sites_urls = catch(
'list', lambda: self.official_sites_df.URI.tolist())
"""
returns: Miscellaneous Sites DataFrame if available.
"""
self.miscellaneous_sites_df = catch(
'None', lambda: external_site(tag_search['miscellaneous'], soup))
self.miscellaneous_sites_names = catch(
'list', lambda: self.miscellaneous_sites_df.Name.tolist())
self.miscellaneous_sites_urls = catch(
'list', lambda: self.miscellaneous_sites_df.URI.tolist())
"""
returns: Photographs Sites DataFrame if available.
"""
self.photographs_sites_df = catch(
'None', lambda: external_site(tag_search['photo'], soup))
self.photographs_sites_names = catch(
'list', lambda: self.photographs_sites_df.Name.tolist())
self.photographs_sites_urls = catch(
'list', lambda: self.photographs_sites_df.URI.tolist())
"""
returns: Videos Clips and Trailers Sites DataFrame if available.
"""
self.videos_clips_and_trailers_sites_df = catch(
'None', lambda: external_site(tag_search['videos'], soup))
self.videos_clips_and_trailers_sites_names = catch(
'list', lambda: self.videos_clips_and_trailers_sites_df.Name.tolist())
self.videos_clips_and_trailers_sites_urls = catch(
'list', lambda: self.videos_clips_and_trailers_sites_df.URI.tolist())
"""
:returns: Creates Meta Data from the above info. if available.
"""
self.imdb_external_sites_metadata = catch('dict', lambda: {"Movie Title": self.title,
"Movie URL": self.external_sites_url,
"Title ID": self.title_id,
"Year": self.year,
"Official Sites": {"Name": self.official_sites_names,
"URL": self.official_sites_urls},
"Miscellaneous Sites": {"Name": self.miscellaneous_sites_names,
"URL": self.miscellaneous_sites_urls},
"Photographs": {"Name": self.photographs_sites_names,
"URL": self.photographs_sites_urls},
"Video Clips and Trailers": {"Name": self.videos_clips_and_trailers_sites_names,
"URL": self.videos_clips_and_trailers_sites_urls}})
def __init__(self):
"""
returns: Country Name & Country Code
"""
soup = BeautifulSoup(get(imdb_uris['calendar']).text, 'lxml')
countries, country_code, = [], []
country = soup.select_one('#sidebar').select('a')
try:
for item in country:
print('%s : %s' % (country.index(item) + 1, item.text.strip()))
countries.append(item.text)
country_code.append(item['href'][17:19].lower())
input_name = re.findall(r"[\w']+", input('Enter serial number\t'))
countries = [
countries[int(load) - 1] if int(load) != 0 else ''
for load in input_name
]
country_code = [
country_code[int(load) - 1] if int(load) != 0 else ''
for load in input_name
]
if len(country_code) == 1:
self.country_name = countries[0]
self.country_code = country_code[0]
else:
self.country_name = countries
self.country_code = country_code
except Exception as es:
print("{0} :".format(type(es)), es)
sys.exit(0)
"""
returns: Upcoming Release for selected regions
"""
self.region_url = imdb_uris['region'] % self.country_code
region_soup = BeautifulSoup(get(self.region_url).text, 'lxml')
try:
release_dates = region_soup.select_one('#pagecontent').select('h4')
self.upcoming_releases_df = pd.DataFrame(
columns=['Release Date', 'Movie Title', 'ID', 'URI', 'Year'])
for item in release_dates:
movies = item.findNext('ul').select('a')
years = item.findNext('ul').select('li')
for i in zip(movies, years):
self.upcoming_releases_df.loc[len(
self.upcoming_releases_df)] = [
catch('None', lambda: unicode(item.get_text())),
catch('None', lambda: unicode(i[0].get_text())),
catch('None', lambda: unicode(i[0]['href'][7:16])),
catch(
'None', lambda: "%s%s" %
(base_uri, unicode(i[0]['href'][1:]))),
catch(
'None', lambda: int(
re.findall(r"\d+", unicode(i[1].contents[2]
))[-1]))
]
self.upcoming_releases_df = dataframe_data(
self.upcoming_releases_df)
except:
self.upcoming_releases_df = None
def __init__(self, title_id):
self.title_id = title_id
self.company_uri = imdb_uris["companycredits"] % self.title_id
soup = BeautifulSoup(get(self.company_uri).text, 'lxml')
"""
:returns: Movie Title
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
:returns: Production Company Credits DataFrame
"""
self.production_company_df = catch(
'None', lambda: company_data(tag_search['production'], soup))
self.production_company_name = catch(
'list', lambda: self.production_company_df.Name.tolist())
self.production_company_id = catch(
'list', lambda: self.production_company_df.ID.tolist())
self.production_company_uri = catch(
'list', lambda: self.production_company_df.URI.tolist())
"""
:returns: Distributors DataFrame
"""
self.distributors_df = catch(
'None', lambda: company_data(tag_search['distributor'], soup))
self.distributors_name = catch(
'list', lambda: self.distributors_df.Name.tolist())
self.distributors_id = catch('list',
lambda: self.distributors_df.ID.tolist())
self.distributors_uri = catch(
'list', lambda: self.distributors_df.URI.tolist())
"""
:returns: Special Effects DataFrame
"""
self.specials_effects_df = catch(
'None', lambda: company_data(tag_search['special_effects'], soup))
self.specials_effects_name = catch(
'list', lambda: self.specials_effects_df.Name.tolist())
self.specials_effects_id = catch(
'list', lambda: self.specials_effects_df.ID.tolist())
self.specials_effects_uri = catch(
'list', lambda: self.specials_effects_df.URI.tolist())
"""
:returns: Other Companies DataFrame
"""
self.other_companies_df = catch(
'None', lambda: company_data(tag_search['other'], soup))
self.other_companies_name = catch(
'list', lambda: self.other_companies_df.Name.tolist())
self.other_companies_id = catch(
'list', lambda: self.other_companies_df.ID.tolist())
self.other_companies_uri = catch(
'list', lambda: self.other_companies_df.URI.tolist())
"""
returns: Creates Dict from the above info. if available.
"""
self.imdb_company_metadata = catch(
'dict', lambda: {
"Movie Name": self.title,
"Movie URI": self.title_url,
"Title ID": self.title_id,
"Year": self.year,
"Movie Company URL": self.company_uri,
"Distributors": {
"Name": self.distributors_name,
"ID": self.distributors_id,
"URI": self.distributors_uri
},
"Other Companies": {
"Name": self.other_companies_name,
"ID": self.other_companies_id,
"URI": self.other_companies_uri
},
"Production Company": {
"Name": self.production_company_name,
"ID": self.production_company_id,
"URI": self.production_company_uri
},
"Special Effects": {
"Name": self.specials_effects_name,
"ID": self.specials_effects_id,
"URI": self.specials_effects_uri
}
})
def __init__(self, title_id: str) -> bool:
self.title_id = title_id
self.movie_uri = imdb_uris["title"] % self.title_id
soup = BeautifulSoup(get(self.movie_uri).text, 'lxml')
"""
:returns: Holds page Info tags
"""
tags = {
'movie':
catch('None', lambda: soup.select_one('h1[class=""]')),
'genre':
catch(
'None', lambda: soup.find('h4', string='Genres:').
findNextSiblings('a')),
'rating':
catch('None',
lambda: soup.select_one('span[itemprop="ratingValue"]')),
'votes':
catch('None',
lambda: soup.select_one('span[itemprop="ratingCount"]')),
'metascore':
catch('None', lambda: soup.select_one('.metacriticScore')),
'summary':
catch('None', lambda: soup.select_one('.summary_text')),
'budget':
catch('None', lambda: soup.find('h4', string='Budget:')),
'opening_weekend_usa':
catch('None',
lambda: soup.find('h4', string='Opening Weekend USA:')),
'gross_usa':
catch('None', lambda: soup.find('h4', string='Gross USA:')),
'cumulative_worldwide_gross':
catch(
'None',
lambda: soup.find('h4', string='Cumulative Worldwide Gross:')),
'poster':
catch('None', lambda: soup.select_one('.poster')),
'year':
catch('None', lambda: soup.select_one('span[id="titleYear"]')),
'review':
catch(
'None', lambda: soup.select_one(
'div[class="titleReviewBarItem titleReviewbarItemBorder"]')
),
'popularity':
catch('None',
lambda: soup.find('div', string=tag_search['popularity']))
}
"""
:returns: Movie Name if available.
"""
self.title = catch('None', lambda: unicode(tags['movie'].contents[0]))
"""
:returns: Genre types for the movie if available.
"""
self.genre = catch(
'list',
lambda: [unicode(genre.get_text()) for genre in tags['genre']])
self.genre_links = catch(
'list', lambda: [
unicode('%s%s' % (base_uri, genre['href'][1:]))
for genre in tags['genre']
])
"""
:returns: IMDb rating for the movie if available.
"""
self.rating = catch('None', lambda: unicode(tags['rating'].get_text()))
"""
:returns: IMDb votes obtained for the movie if available.
"""
self.votes = catch('None', lambda: digits(tags['votes'].get_text()))
"""
:returns: Metascore of the movie if available.
"""
self.metascore = catch('None',
lambda: unicode(tags['metascore'].get_text()))
self.metascore_uri = catch(
'None', lambda: unicode("%s/%s" % (self.movie_uri, tags[
'metascore'].findParent('a')['href'])))
"""
:returns: Movie User Review info if available.
"""
self.user_review_count = catch(
'None', lambda: digits(tags['review'].select_one(
'a[href="reviews"]').get_text()))
self.user_review_uri = catch(
'None', lambda: "%s/%s" % (self.movie_uri, tags[
'review'].select_one('a[href="reviews"]')['href']))
"""
:returns: Movie Critic Review info if available.
"""
self.critic_review_count = catch(
'None', lambda: digits(tags['review'].select_one(
'a[href="externalreviews"]').get_text()))
self.critic_review_uri = catch(
'None', lambda: "%s/%s" % (self.movie_uri, tags[
'review'].select_one('a[href="externalreviews"]')['href']))
"""
:returns: Popularity of the movie if available.
"""
self.popularity_initial = catch(
'None',
lambda: digits(tags['popularity'].findNext('span').contents[0]))
self.popularity_name = catch(
'None', lambda: tags['popularity'].findNext(
'span', class_='titleOverviewSprite').findNext('span')['class']
[0])
self.popularity_value = catch(
'None', lambda: digits(tags['popularity'].findNext(
'span', class_='titleOverviewSprite').findNext('span').
get_text()))
"""
:returns: Storyline of the movie if available.
"""
self.storyline = catch('None',
lambda: unicode(tags['summary'].get_text()))
"""
:returns: Budget of the movie if available.
"""
self.budget = catch('None',
lambda: unicode(tags['budget'].nextSibling))
"""
:returns: Opening Weekend USA of the movie if available.
"""
self.opening_weekend_usa = catch(
'None', lambda: unicode(tags['opening_weekend_usa'].nextSibling))
"""
:returns: Gross USA of the movie if available.
"""
self.gross_usa = catch('None',
lambda: unicode(tags['gross_usa'].nextSibling))
"""
:returns: Cumulative Worldwide Gross of the movie if available.
"""
self.cumulative_worldwide_gross = catch(
'None',
lambda: unicode(tags['cumulative_worldwide_gross'].nextSibling))
"""
:returns: Movie Poster URL if available.
"""
self.movie_poster_uri = catch(
'None', lambda: unicode('%s%s' %
(base_uri, tags['poster'].a['href'][1:])))
"""
:returns: Movie Released Year if available.
"""
self.movie_release_year = catch(
'None', lambda: unicode(tags['year'].a.get_text()))
self.movie_release_year_link = catch(
'None',
lambda: unicode(imdb_uris['year'] % self.movie_release_year))
"""
:returns: Creates Meta Data from the above info. if available.
"""
self.imdb_movie_metadata = catch(
'dict', lambda: {
"Movie Name": self.title,
"Movie URI": self.movie_uri,
"Title ID": self.title_id,
"Rating": self.rating,
"IMDb Votes": self.votes,
"Genre": self.genre,
"Genre Links": self.genre_links,
"Year": self.movie_release_year,
"Year Links": self.movie_release_year_link,
"Metascore": self.metascore,
"Metascore Link": self.metascore_uri,
"User Review Count": self.user_review_count,
"User Review Link": self.user_review_uri,
"Critic Review Count": self.critic_review_count,
"Critic Review Link": self.critic_review_uri,
"Popularity Initial": self.popularity_initial,
"Popularity Name": self.popularity_name,
"Popularity value": self.popularity_value,
"Movie Poster URI": self.movie_poster_uri,
"Budget": self.budget,
"Opening Weekend USA": self.opening_weekend_usa,
"Cumulative Worldwide Gross": self.cumulative_worldwide_gross,
"Gross USA": self.gross_usa,
"Storyline": self.storyline
})
def __init__(self, title_id: str, remove_spoiler: False):
self.title_id = title_id
if remove_spoiler is False:
self.user_reviews_url = imdb_uris['reviews'] % self.title_id
else:
self.user_reviews_url = imdb_uris['spoiler_reviews'] % self.title_id
# Creating soup for the website
soup = BeautifulSoup(get(self.user_reviews_url).text, 'lxml')
"""
:returns: movie title if available.
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
# for collection of number of reviews
reviews_count = catch(
'None', lambda: digits(soup.select_one('div.header').span.text))
maxclicks = catch('None', lambda: int(reviews_count) // 25)
options = Options()
options.add_argument("--headless")
browser = webdriver.Chrome(options=options)
wait = WebDriverWait(browser, 100)
browser.get(self.user_reviews_url)
clicks = 0
while True:
clicks += 1
if clicks <= maxclicks:
wait.until(
ec.visibility_of_element_located(
(By.CLASS_NAME, "ipl-load-more__button"))).click()
else:
break
sys.stdout.write(
"\r%s - clicks has made for scrolling out of - %s\r" %
(str(clicks), str(maxclicks)))
sys.stdout.flush()
time.sleep(1)
soup = BeautifulSoup(browser.page_source, 'lxml')
browser.quit()
container = soup.select('.review-container')
self.total_user_reviews = len(container)
analyser = SentimentIntensityAnalyzer()
neu_sum, neg_sum, compound_sum, pos_sum, count = [0] * 5
self.user_reviews_df = catch('None',
lambda: review_df(analyser, container))
self.user_reviews = catch(
'list', lambda: self.user_reviews_df.User_Reviews.tolist())
for review in self.user_reviews:
count += 1
score = analyser.polarity_scores(review)
neu_sum += score['neu']
neg_sum += score['neg']
pos_sum += score['pos']
if count:
self.final_sentiment_scores = catch(
'None', lambda: {
"neu": round(neu_sum / count, 3),
"neg": round(neg_sum / count, 3),
"pos": round(pos_sum / count, 3),
"compound": round(compound_sum / count, 3)
})
def __init__(self, title_id):
self.title_id = title_id
self.parental_guide_url = imdb_uris["parentalguide"] % self.title_id
soup = BeautifulSoup(get(self.parental_guide_url).text, 'lxml')
"""
:returns: Movie Title
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
:returns: MPAA available.
"""
mpaa = catch(
'None', lambda: soup.select_one(tag_search['certificates']).
select_one(tag_search['mpaa']))
mpaa_tag = catch(
'None',
lambda: mpaa.select_one('td[class="ipl-zebra-list__label"]'))
self.mpaa_name = catch('None', lambda: unicode(mpaa_tag.get_text()))
self.mpaa_description = catch(
'None', lambda: unicode(mpaa_tag.findNext('td').get_text()))
"""
:returns: Certificate DataFrame if available.
"""
try:
certificates = catch(
'None', lambda: soup.select_one(tag_search['certificates']).
select_one(tag_search['certifications']).find(
'td', string='Certification').findNextSibling('td').select(
'li.ipl-inline-list__item'))
self.certificates_df = pd.DataFrame(columns=['Name', 'URI'])
for tag in certificates:
self.certificates_df.loc[len(self.certificates_df)] = [
catch('None', lambda: unicode(tag.a.get_text())),
catch(
'None', lambda: unicode("%s%s" %
(base_uri, tag.a['href'][1:])))
]
self.certificates_df = dataframe_data(self.certificates_df)
except:
self.certificates_df = None
self.certificates_name = catch(
'list', lambda: self.certificates_df.Name.tolist())
self.certificates_uri = catch(
'list', lambda: self.certificates_df.URI.tolist())
"""
:returns: Adivsory Nudity status if available.
"""
advisory = catch(
'None', lambda: soup.select_one(tag_search['advisory-nudity']))
severity = catch('None',
lambda: advisory.select_one(tag_search['nudity']))
self.adivsory_nudity_severity_status = catch(
'dict', lambda: adivsory_satus(severity))
self.advisory_nudity_reviews = catch(
'list', lambda: advisory_reviews(advisory))
"""
:returns: Adivsory Violence status if available.
"""
advisory = catch(
'None', lambda: soup.select_one(tag_search['advisory-violence']))
severity = catch('None',
lambda: advisory.select_one(tag_search['violence']))
self.advisory_violence_severity_status = catch(
'dict', lambda: adivsory_satus(severity))
self.advisory_violence_reviews = catch(
'list', lambda: advisory_reviews(advisory))
"""
:returns: Adivsory Profanity status if available.
"""
advisory = catch(
'None', lambda: soup.select_one(tag_search['advisory-profanity']))
severity = catch('None',
lambda: advisory.select_one(tag_search['profanity']))
self.advisory_profanity_severity_status = catch(
'dict', lambda: adivsory_satus(severity))
self.advisory_profanity_reviews = catch(
'list', lambda: advisory_reviews(advisory))
"""
:returns: Adivsory Alcohol status if available.
"""
advisory = catch(
'None', lambda: soup.select_one(tag_search['advisory-alcohol']))
severity = catch('None',
lambda: advisory.select_one(tag_search['alcohol']))
self.advisory_alcohol_severity_status = catch(
'dict', lambda: adivsory_satus(severity))
self.advisory_alcohol_reviews = catch(
'list', lambda: advisory_reviews(advisory))
"""
:returns: Adivsory Frightening status if available.
"""
advisory = catch(
'None',
lambda: soup.select_one(tag_search['advisory-frightening']))
severity = catch(
'None', lambda: advisory.select_one(tag_search['frightening']))
self.advisory_frightening_severity_status = catch(
'dict', lambda: adivsory_satus(severity))
self.advisory_frightening_reviews = catch(
'list', lambda: advisory_reviews(advisory))
"""
:returns: Spoilers Violence & Gore if available.
"""
advisory = catch(
'None', lambda: soup.select_one(tag_search['advisory-spoilers']).
select_one('section[id="advisory-spoiler-violence"]'))
self.spoiler_violence_reviews = catch(
'list', lambda: advisory_reviews(advisory))
"""
:returns: Spoilers Alcohol, Drugs & Smoking if available.
"""
advisory = catch(
'None', lambda: soup.select_one(tag_search['advisory-spoilers']).
select_one('section[id="advisory-spoiler-profanity"]'))
self.spoiler_alcohol_reviews = catch(
'list', lambda: advisory_reviews(advisory))
"""
:returns: Spoilers Frightening & Intense Scenes if available.
"""
advisory = catch(
'None', lambda: soup.select_one(tag_search['advisory-spoilers']).
select_one('section[id="advisory-spoiler-frightening"]'))
self.spoiler_frightening_reviews = catch(
'list', lambda: advisory_reviews(advisory))
"""
:returns: Creates Dict from the above info. if available.
"""
self.imdb_parental_guide_metadata = catch(
'dict', lambda: {
"Movie Name": self.title,
"Movie URI": self.title_url,
"Title ID": self.title_id,
"Year": self.year,
"Movie Parental Guide URL": self.parental_guide_url,
"MPAA Name": self.mpaa_name,
"MPAA Description": self.mpaa_description,
"Certificate": self.certificates_name,
"Certificate URI": self.certificates_uri,
"Sex & Nudity": {
"Nudity Severity": self.adivsory_nudity_severity_status,
"Nudity Review": self.advisory_nudity_reviews
},
"Alcohol & Smoking": {
"Alcohol Severity": self.advisory_alcohol_severity_status,
"Alcohol Review": self.advisory_alcohol_reviews
},
"Violence": {
"Violence Severity": self.
advisory_violence_severity_status,
"Violence Review": self.advisory_violence_reviews
},
"Frighten": {
"Frighten Severity": self.
advisory_frightening_severity_status,
"Frighten Review": self.advisory_frightening_reviews
},
"Profanity": {
"Profanity Severity": self.
advisory_profanity_severity_status,
"Profanity Review": self.advisory_profanity_reviews
},
"Spoiler Violence": self.spoiler_violence_reviews,
"Spoiler Alcohol": self.spoiler_alcohol_reviews,
"Spoiler Frighten": self.spoiler_frightening_reviews
})
def __init__(self, title_id: str) -> bool:
self.title_id = title_id
self.full_cast_and_crew_uri = imdb_uris["fullcredits"] % self.title_id
soup = BeautifulSoup(get(self.full_cast_and_crew_uri).text, 'lxml')
"""
:returns: table tag index
"""
table_tag = catch('None', lambda: soup.select('h4'))
"""
:returns: Movie Title
"""
movie_tag = catch('None',
lambda: soup.select_one('h3[itemprop="name"]'))
self.title = catch('None', lambda: unicode(movie_tag.a.get_text()))
self.title_url = catch(
'None', lambda: unicode('%s%s' %
(base_uri, movie_tag.a['href'][1:])))
self.year = catch(
'None', lambda: int(
re.findall(r"\d+",
unicode(movie_tag.select_one('.nobr').get_text()))[
0]))
"""
:returns: Writtern Credits DataFrame
"""
self.writers_df = catch(
'None', lambda: cast_credit(tag_search['writer'], table_tag))
self.writers_name = catch('list',
lambda: self.writers_df.Name.tolist())
self.writers_id = catch('list', lambda: self.writers_df.ID.tolist())
self.writers_uri = catch('list', lambda: self.writers_df.URI.tolist())
self.writers_credit = catch('list',
lambda: self.writers_df.Credit.tolist())
"""
:returns: Directed_by DataFrame
"""
self.directors_df = catch(
'None', lambda: cast_non_credit(tag_search['director'], table_tag))
self.directors_name = catch('list',
lambda: self.directors_df.Name.tolist())
self.directors_id = catch('list',
lambda: self.directors_df.ID.tolist())
self.directors_uri = catch('list',
lambda: self.directors_df.URI.tolist())
"""
:returns: Produced_by DataFrame
"""
self.producers_df = catch(
'None', lambda: cast_non_credit(tag_search['producer'], table_tag))
self.producers_name = catch('list',
lambda: self.producers_df.Name.tolist())
self.producers_id = catch('list',
lambda: self.producers_df.ID.tolist())
self.producers_credit = catch(
'list', lambda: self.producers_df.Credit.tolist())
self.producers_uri = catch('list',
lambda: self.producers_df.URI.tolist())
"""
:returns: Cast DataFrame
"""
self.cast_df = catch('None',
lambda: full_cast(tag_search['cast'], table_tag))
self.cast_name = catch('list', lambda: self.cast_df.Name.tolist())
self.cast_id = catch('list', lambda: self.cast_df.Name_ID.tolist())
self.cast_uri = catch('list', lambda: self.cast_df.Name_URI.tolist())
self.cast_image_uri = catch('list',
lambda: self.cast_df.Image.tolist())
self.cast_character = catch(
'list', lambda: self.cast_df.Character_Name.tolist())
self.cast_character_id = catch(
'list', lambda: self.cast_df.Character_ID.tolist())
self.cast_character_uri = catch(
'list', lambda: self.cast_df.Character_URI.tolist())
"""
:returns: Music by DataFrame
"""
self.music_df = catch(
'None', lambda: cast_non_credit(tag_search['music'], table_tag))
self.music_name = catch('list', lambda: self.music_df.Name.tolist())
self.music_id = catch('list', lambda: self.music_df.ID.tolist())
self.music_uri = catch('list', lambda: self.music_df.URI.tolist())
"""
:returns: Cinematography by DataFrame
"""
self.cinematography_df = catch(
'None',
lambda: cast_non_credit(tag_search['cinematography'], table_tag))
self.cinematography_name = catch(
'list', lambda: self.cinematography_df.Name.tolist())
self.cinematography_id = catch(
'list', lambda: self.cinematography_df.ID.tolist())
self.cinematography_uri = catch(
'list', lambda: self.cinematography_df.URI.tolist())
"""
:returns: Production Design by DataFrame
"""
self.production_designer_df = catch(
'None', lambda: cast_non_credit(tag_search['production design'],
table_tag))
self.production_designer_name = catch(
'list', lambda: self.production_designer_df.Name.tolist())
self.production_designer_id = catch(
'list', lambda: self.production_designer_df.ID.tolist())
self.production_designer_uri = catch(
'list', lambda: self.production_designer_df.URI.tolist())
"""
:returns: Film Editing by DataFrame
"""
self.film_editing_df = catch(
'None', lambda: cast_credit(tag_search['film editing'], table_tag))
self.film_editing_name = catch(
'list', lambda: self.film_editing_df.Name.tolist())
self.film_editing_id = catch('list',
lambda: self.film_editing_df.ID.tolist())
self.film_editing_credit = catch(
'list', lambda: self.film_editing_df.Credit.tolist())
self.film_editing_uri = catch(
'list', lambda: self.film_editing_df.URI.tolist())
"""
:returns: Casting by DataFrame
"""
self.casting_df = catch(
'None', lambda: cast_credit(tag_search['casting'], table_tag))
self.casting_name = catch('list',
lambda: self.casting_df.Name.tolist())
self.casting_id = catch('list', lambda: self.casting_df.ID.tolist())
self.casting_credit = catch('list',
lambda: self.casting_df.Credit.tolist())
self.casting_uri = catch('list', lambda: self.casting_df.URI.tolist())
"""
:returns: Creates Dict from the above info. if available.
"""
self.imdb_full_cast_and_crew_metadata = catch(
'dict', lambda: {
"Movie Name": self.title,
"Movie URL": self.title_url,
"Title ID": self.title_id,
"Year": self.year,
"Movie Full Cast and Crew URI": self.full_cast_and_crew_uri,
"Director": {
"Name": self.directors_name,
"ID": self.directors_id,
"URI": self.directors_uri
},
"Writer": {
"Name": self.writers_name,
"Credit": self.writers_credit,
"ID": self.writers_id,
"URI": self.writers_uri
},
"Cast": {
"Name": self.cast_name,
"Name ID": self.cast_id,
"Name URI": self.cast_uri,
"Image": self.cast_image_uri,
"Character Name": self.cast_character,
"Characte ID": self.cast_character_id,
"Characte URI": self.cast_character_uri
},
"Producer": {
"Name": self.producers_name,
"Credit": self.producers_credit,
"ID": self.producers_id,
"URI": self.producers_uri
},
"Music": {
"Name": self.music_name,
"ID": self.music_id,
"URI": self.music_uri
},
"Cinematography": {
"Name": self.cinematography_name,
"ID": self.cinematography_id,
"URI": self.cinematography_uri
},
"Production Desing": {
"Name": self.production_designer_name,
"ID": self.production_designer_id,
"URI": self.production_designer_uri
},
"Flim Editing": {
"Name": self.film_editing_name,
"Credit": self.film_editing_credit,
"ID": self.film_editing_id,
"URI": self.film_editing_uri
},
"Casting": {
"Name": self.casting_name,
"Credit": self.casting_credit,
"ID": self.casting_id,
"URI": self.casting_uri
}
})