0x2620/python-oxweb
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

wikipedia by amg_id, only one place to keep the criterion poster url

Browse source
This commit is contained in:
j 2008-05-10 11:10:23 +02:00
parent 37bd88fa4a
commit 26f82c01b4
2 changed files with 15 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
ox/criterion.py
View file

@ -15,7 +15,7 @@ def getData(criterionId):
data = {} data = {}
html = getUrlUnicode('http://criterion.com/asp/release.asp?id=%s' % criterionId) html = getUrlUnicode('http://criterion.com/asp/release.asp?id=%s' % criterionId)
data['criterionId'] = criterionId data['criterionId'] = criterionId
data['posterUrl'] = 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % criterionId data['posterUrl'] = getPosterUrl(criterionId)
data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>')) data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>'))
result = re.compile("<title>The Criterion Collection: (.*?) by (.*?)</title>").findall(html) result = re.compile("<title>The Criterion Collection: (.*?) by (.*?)</title>").findall(html)
data['title'] = stripTags(result[0][0]) data['title'] = stripTags(result[0][0])
@ -27,6 +27,9 @@ def getCriterionIds():
html = getUrlUnicode('http://criterion.com/asp/list.asp?sort=spine') html = getUrlUnicode('http://criterion.com/asp/list.asp?sort=spine')
return re.compile('release.asp\?id=(.*?)"').findall(html) return re.compile('release.asp\?id=(.*?)"').findall(html)
def getPosterUrl(criterionId):
return 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % criterionId
def getMovieId(title = '', director = '', imdbId = ''): def getMovieId(title = '', director = '', imdbId = ''):
if not imdbId: if not imdbId:
imdbId = imdb.getMovieId(title, director) imdbId = imdb.getMovieId(title, director)
@ -51,7 +54,7 @@ def getMovieData(title = '', director = '', imdbId = ''):
if id: if id:
html = getUrlUnicode('http://criterion.com/asp/release.asp?id=%s' % id) html = getUrlUnicode('http://criterion.com/asp/release.asp?id=%s' % id)
data['id'] = id data['id'] = id
data['posterUrl'] = 'http://criterion.com/content/images/full_boxshot/%s_box_348x490.jpg' % id data['posterUrl'] = getPosterUrl(id)
data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>')) data['synopsis'] = stripTags(findRe(html, '<h3>Synopsis</h3>(.*?)</div>'))
return data return data

10
ox/wikipedia.py
View file

@ -24,11 +24,21 @@ def getUrlByImdb(imdbId):
return url return url
return '' return ''
def getUrlByAmbId(amg_id):
query = '"amg_id = %s"'% amg_id
result = find(query)
if result:
url = result[0][1]
return url
return ''
def find(query, max_results=10): def find(query, max_results=10):
query = {'action': 'query', 'list':'search', 'format': 'json', query = {'action': 'query', 'list':'search', 'format': 'json',
'srlimit': max_results, 'srwhat': 'text', 'srsearch': query.encode('utf-8')} 'srlimit': max_results, 'srwhat': 'text', 'srsearch': query.encode('utf-8')}
url = "http://en.wikipedia.org/w/api.php?" + urlencode(query) url = "http://en.wikipedia.org/w/api.php?" + urlencode(query)
data = getUrl(url) data = getUrl(url)
if not data:
data = getUrl(url, timeout=0)
result = simplejson.loads(data) result = simplejson.loads(data)
results = [] results = []
for r in result['query']['search']: for r in result['query']['search']: