def imdb(self):
"""Get IMDb data for release, set self.imdb_id to override auto match
from movie title + year"""
from imdbpie import Imdb
imdb = Imdb()
if not self.movie_release:
return False
imdb_id = None
if hasattr(self, "imdb_id"):
imdb_id = self.imdb_id
# Find IMDb match by title and check if year is a match
if not imdb_id:
for imdb_match in imdb.find_by_title(self.movie_title):
if int(imdb_match.get("year")) == self.movie_year:
imdb_id = imdb_match.get("imdb_id")
break
# No IMDb match could be found from title + year
if not imdb_id:
return False
return imdb.find_movie_by_id(imdb_id)
def net_search(name):
#input=movie name
#output=movie id from imdb
imdb = Imdb({'anonymize': False})
#~ movie = imdb.find_movie_by_id("tt0382932")
#~ print movie.title
if len(name) > 0:
details = imdb.find_by_title(name)
if len(details) > 0:
#~ return imdb.find_movie_by_id(details[0]['imdb_id'])
imdb_id = details[0]['imdb_id']
#~ print imdb_id
movie = imdb.find_movie_by_id(imdb_id)
return movie
else:
#~ return NULL
return -1
def net_search(name):
#input=movie name
#output=movie id from imdb
imdb = Imdb({'anonymize': False})
#~ movie = imdb.find_movie_by_id("tt0382932")
#~ print movie.title
if len(name)>0:
details=imdb.find_by_title(name)
if len(details)>0:
#~ return imdb.find_movie_by_id(details[0]['imdb_id'])
imdb_id=details[0]['imdb_id']
#~ print imdb_id
movie=imdb.find_movie_by_id(imdb_id)
return movie
else:
#~ return NULL
return -1
audience_score = re.findall(pattern,movie_details)
text = '"critics_score":"(.+?)"'
pattern = re.compile(text)
critics_score = re.findall(pattern,movie_details)
c.execute("INSERT INTO Rottentomatoes_movie VALUES(name,year,mpaa_rating,release_date,audience_score,critics_score")
conn.commit()
print "Details from Rottentomatoes:\n"
for row in c.execute('SELECT * FROM Rottentomatoes_movie ORDER audience_score'):
print row
conn.close()
imdb = Imdb()
imdb.find_by_title(movie)
c.execute('''CREATE TABLE IF NOT EXISTS imdb_movie(name text,year int,mpaa_rating text,release_date text,genre text,runtime text,plot text,language text,director text,writer text,actors text,metascore real,imdb_rating real,imdb_votes int)''')
text = '"Title":"(.+?)"'
pattern = re.compile(text)
name = re.findall(pattern,movie_details)
text = '"Year":"(.+?)"'
pattern = re.compile(text)
year = re.findall(pattern,movie_details)
text = '"Rated":"(.+?)"'
pattern = re.compile(text)
mpaa_rating = re.findall(pattern,movie_details)
text = '"Released":"(.+?)"'
def details(movie,detailinfo):
imdb = Imdb()
movie_data=imdb.find_by_title(movie)
json_data = json.loads(movie_data)[0]
detail = json_data[detailinfo]
return detail
print 'usage: imdb_downloader.py [movie name | top50 | top250]'
sys.exit(1)
if sys.argv[1] == "top50":
print "Retrieving Top 50 movies"
top50 = imdb.top_250()[0:50]
for m in top50:
movies_xml.getroot().append(get_movie(m['tconst']))
elif sys.argv[1] == "top250":
print "Retrieving Top 250 movies"
top50 = imdb.top_250()
for m in top50:
movies_xml.getroot().append(get_movie(m['tconst']))
else:
movie = imdb.find_by_title(sys.argv[1])[0]
if movie is None:
print 'Not found.'
sys.exit(1)
movie_xml = get_movie(movie['imdb_id'])
movies_xml.getroot().append(movie_xml)
f = open('data/movies.xml', 'w')
f.write(etree.tostring(movies_xml.getroot(), pretty_print=True))
f.close()
