Created
May 11, 2009 06:39
-
-
Save csytan/109890 to your computer and use it in GitHub Desktop.
imdb.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from lib import BeautifulSoup | |
import urllib2 | |
from urlparse import urljoin | |
import difflib | |
import re | |
def get_title_name(self): | |
imdb_title = self.title_id | |
url = urllib2.urlopen("http://imdb.com/title/" + imdb_title) | |
string = url.read() | |
soup = BeautifulSoup.BeautifulSoup(string) | |
title = soup('title')[0] | |
return title.string | |
def get_imdb_rating(self): | |
imdb_title = self.title_id | |
url = urllib2.urlopen("http://imdb.com/title/" + imdb_title) | |
string = url.read() | |
soup = BeautifulSoup.BeautifulSoup(string) | |
for div in soup('div'): | |
if 'class' in dict(div.attrs) and div['class']=='general rating': | |
for b in div('b'): | |
if b.contents[0] == 'User Rating:': | |
pass | |
else: | |
rating = b.contents[0].rstrip("/10") | |
return float(rating) | |
return None | |
def search_imdb(self, search_string): | |
""" | |
Returns the title of the first match in IMDb's title search | |
""" | |
query = search_string.replace(" ", "+") | |
try: | |
page = urllib2.urlopen("http://imdb.com/find?s=tt&q=" + query) | |
except: | |
print "Could not open %s" % page | |
return None | |
# if redirected to imdb page (exact match) | |
if 'imdb.com/title/' in page.url: | |
titlePattern = re.compile("imdb.com/title/(tt\d+)/?") | |
results = titlePattern.findall(page.url) | |
if results is not None: | |
return results[0] | |
soup = BeautifulSoup.BeautifulSoup(page.read()) | |
matcher = difflib.SequenceMatcher() | |
links = soup('a') | |
best_ratio = 0 | |
for link in links: | |
if 'href' in dict(link.attrs): | |
if not link.has_key('onclick'): | |
if "/title/" in link['href']: | |
matcher.set_seqs(search_string, link.contents[0]) | |
ratio = matcher.ratio() | |
if ratio > best_ratio: | |
best_ratio = ratio | |
title = link['href'].replace('/title/', '').replace('/', '') | |
if best_ratio > 0.80: | |
return title | |
else: | |
return None | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment