0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

include first poster

Browse source
This commit is contained in:
j 2010-08-12 13:54:22 +02:00
parent 0f74f3efff
commit f73e043d64
1 changed files with 5 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
ox/web/impawards.py
View file

@ -23,10 +23,14 @@ def getData(id):
'url': getUrl(id) 'url': getUrl(id)
} }
html = readUrlUnicode(data['url']) html = readUrlUnicode(data['url'])
data['imdbId'] = findRe(html, 'imdb.com/title/tt(.*?) ') data['imdbId'] = findRe(html, 'imdb.com/title/tt(\d{7})')
data['title'] = stripTags(findRe(html, '<p class="name white">(.*?) \(<a href="alpha1.html">')) data['title'] = stripTags(findRe(html, '<p class="name white">(.*?) \(<a href="alpha1.html">'))
data['year'] = findRe(html, '\(<a href="alpha1.html">(.*?)</a>\)') data['year'] = findRe(html, '\(<a href="alpha1.html">(.*?)</a>\)')
data['posters'] = [] data['posters'] = []
poster = findRe(html, '<img src="(posters.*?)" alt=')
if poster:
poster = 'http://www.impawards.com/%s/%s' % (data['year'], poster)
data['posters'].append(poster)
results = re.compile('<a href = (%s.*?html)' % id[5:], re.DOTALL).findall(html) results = re.compile('<a href = (%s.*?html)' % id[5:], re.DOTALL).findall(html)
for result in results: for result in results:
result = result.replace('_xlg.html', '.html') result = result.replace('_xlg.html', '.html')