python-ox/ox/web/metacritic.py

64 lines
2.1 KiB
Python
Raw Normal View History

2010-07-07 23:25:57 +00:00
# -*- coding: utf-8 -*-
# vi:si:et:sw=4:sts=4:ts=4
import re
from urllib import quote
2012-07-08 11:09:58 +00:00
from lxml.html import document_fromstring
2010-07-07 23:25:57 +00:00
from ox.cache import read_url
from ox import find_re, strip_tags
2010-07-07 23:25:57 +00:00
2012-08-15 15:15:40 +00:00
def get_url(id=None, imdb=None):
if imdb:
url = "http://www.imdb.com/title/tt%s/criticreviews" % imdb
data = read_url(url)
metacritic_url = find_re(data, '"(http://www.metacritic.com/movie/.*?)"')
return metacritic_url or None
2012-07-08 11:16:59 +00:00
return 'http://www.metacritic.com/movie/%s' % id
2012-08-15 15:15:40 +00:00
def get_id(url):
2012-07-08 11:16:59 +00:00
return url.split('/')[-1]
2012-08-15 15:15:40 +00:00
def get_show_url(title):
2010-07-07 23:25:57 +00:00
title = quote(title)
url = "http://www.metacritic.com/search/process?ty=6&ts=%s&tfs=tvshow_title&x=0&y=0&sb=0&release_date_s=&release_date_e=&metascore_s=&metascore_e=" % title
data = read_url(url)
return find_re(data, '(http://www.metacritic.com/tv/shows/.*?)\?')
2010-07-07 23:25:57 +00:00
2012-08-15 15:15:40 +00:00
def get_data(url):
data = read_url(url, unicode=True)
2012-07-08 11:09:58 +00:00
doc = document_fromstring(data)
score = filter(lambda s: s.attrib.get('property') == 'v:average',
doc.xpath('//span[@class="score_value"]'))
if score:
score = int(score[0].text)
else:
score = -1
authors = [a.text
for a in doc.xpath('//div[@class="review_content"]//div[@class="author"]//a')]
2012-07-08 11:16:59 +00:00
sources = [d.text
2012-07-08 11:09:58 +00:00
for d in doc.xpath('//div[@class="review_content"]//div[@class="source"]/a')]
reviews = [d.text
for d in doc.xpath('//div[@class="review_content"]//div[@class="review_body"]')]
scores = [int(d.text.strip())
for d in doc.xpath('//div[@class="review_content"]//div[contains(@class, "critscore")]')]
2012-07-08 11:16:59 +00:00
urls = [a.attrib['href']
2012-07-08 11:09:58 +00:00
for a in doc.xpath('//div[@class="review_content"]//a[contains(@class, "external")]')]
2010-07-07 23:25:57 +00:00
2012-07-08 11:09:58 +00:00
metacritics = []
for i in range(len(authors)):
metacritics.append({
'critic': authors[i],
2012-07-08 11:16:59 +00:00
'url': urls[i],
'source': sources[i],
'quote': strip_tags(reviews[i]).strip(),
2012-07-08 11:16:59 +00:00
'score': scores[i],
2012-07-08 11:09:58 +00:00
})
return {
2012-07-08 11:16:59 +00:00
'critics': metacritics,
2012-08-15 15:15:40 +00:00
'id': get_id(url),
2012-07-08 11:16:59 +00:00
'score': score,
'url': url,
2012-07-08 11:09:58 +00:00
}
2010-07-07 23:25:57 +00:00