# https://github.com/richardasaurus/imdb-pie
from imdbpie import Imdb
imdb = Imdb()
imdb = Imdb(anonymize=True)
print(imdb.search_for_title("The Dark Knight"))
print()
print(imdb.search_for_person("Christian Bale"))
print()
print(imdb.get_episodes('tt0096697'))
top250 = imdb.top_250()
for i in range(0, len(top250)):
print(top250[i])
print()
title = imdb.get_title_by_id("tt1210166")
for person in title.credits:
# check if they are a writer
if person.token == 'writers':
print(person.name + ' is a writer')
else:
print(person.name + ' is not a writer')
def imdb_content(twitter_id, twitter_name):
imdb = Imdb()
# imdb = Imdb(anonymize=True) # to proxy requests
id = imdb.search_for_person(twitter_name)[0]['imdb_id']
hxs = lxml.html.document_fromstring(
requests.get("http://www.imdb.com/name/" + str(id)).content)
name = ''
try:
name = hxs.xpath('//*[@id="overview-top"]/h1/span/text()')[0].strip()
except:
#try:
# name = hxs.xpath('//*[@id="overview-top"]/div[1]/div/h1/span/text()')[0].strip()
#except:
# pass
pass
if name.lower() == twitter_name.lower():
try:
occupation = [
o.strip() for o in hxs.xpath(
'//*[@id="name-job-categories"]/a[*]/span/text()')
]
except:
occupation = ''
try:
birthday = hxs.xpath(
'//*[@id="name-born-info"]/time')[0].attrib['datetime']
except:
birthday = ''
try:
death = hxs.xpath(
'//*[@id="name-death-info"]/time')[0].attrib['datetime']
except:
death = ""
hxs_bio = lxml.html.document_fromstring(
requests.get("http://www.imdb.com/name/" + id + "/bio").content)
try:
content = ''.join(
hxs_bio.xpath('//*[@id="bio_content"]/div[2]/p[1]/text()'))
except:
content = ''
try:
spouse = hxs_bio.xpath(
'//*[@id="tableSpouses"]//tr/td[1]/a/text()')
except:
spouse = ''
try:
children_content = hxs_bio.xpath(
'//*[@id="tableSpouses"]//tr/td[2]/text()')
children = 0
for line in children_content:
l = line.encode('UTF-8').replace('(', '( ').strip()
pattern = '(.*) (.*) child'
compiled = re.compile(pattern)
m = compiled.search(l)
if m is not None:
children += int(m.group(2))
except:
children = ''
basic_info = {
'id': twitter_id,
'name': name,
'occupation': occupation,
'birthday': birthday,
'death': death,
'spouse': spouse,
'children': str(children)
}
content_info = {'id': twitter_id, 'content': content.strip()}
write_imdb_data(json.dumps(basic_info), json.dumps(content_info))
actor_names = []
names = pd.read_excel('Actor_names.xlsx')
n = names.iterrows()
actor_names = []
actor_ids = []
for i in n:
actor_names.append(i[1][0])
print len(actor_names)
for name in actor_names:
try:
actor_name = imdb.search_for_person(str(name))
except:
continue
print 'Converting ' + str(name) + ' to IMDB id: ' + str(actor_name[0]['imdb_id'].replace('nm',''))
actor_ids.append(actor_name[0]['imdb_id'].replace('nm',''))
print 'Total actor count: ' + str(len(actor_ids))
no_pic = []
ids = pd.DataFrame(actor_ids)
ac_ids = {}
ac_ages = {}
ac_names = []
ac_pred_age = []
actor_ids = []
actor_names = []
names = pd.read_excel('Actor_names.xlsx')
n = names.iterrows()
actor_names = []
actor_ids = []
for i in n:
actor_names.append(i[1][0])
print len(actor_names)
for name in actor_names:
try:
actor_name = imdb.search_for_person(str(name))
except:
continue
print 'Converting ' + str(name) + ' to IMDB id: ' + str(
actor_name[0]['imdb_id'].replace('nm', ''))
actor_ids.append(actor_name[0]['imdb_id'].replace('nm', ''))
print 'Total actor count: ' + str(len(actor_ids))
no_pic = []
ids = pd.DataFrame(actor_ids)
ac_ids = {}
ac_ages = {}
ac_names = []
ac_pred_age = []
