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

allmovie: more data

Browse source
This commit is contained in:
Rolux 2008-07-25 16:35:12 +02:00
parent 314fd03934
commit aee1085e35
1 changed files with 8 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

9
oxweb/allmovie.py
View file

@ -10,7 +10,6 @@ def getMovieData(allmovieId):
html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T0" % allmovieId) html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T0" % allmovieId)
data = {} data = {}
data['poster'] = findRe(html, '<img src="(http://image.*?)"') data['poster'] = findRe(html, '<img src="(http://image.*?)"')
data['synopsis'] = stripTags(findRe(html, 'Plot Synopsis</td>.*?<td colspan="2"><p>(.*?)</td>'))
data['year'] = findRe(html, '<a href="/cg/avg.dll\?p=avg&amp;sql=24:\d{4}">(\d{4})</a>') data['year'] = findRe(html, '<a href="/cg/avg.dll\?p=avg&amp;sql=24:\d{4}">(\d{4})</a>')
data['rating'] = findRe(html, '" alt="(\d+?) Stars"') data['rating'] = findRe(html, '" alt="(\d+?) Stars"')
data['country'] = findRe(html, '<a href="/cg/avg.dll\?p=avg&sql=24:D\|\|\|206">(.*?)</') data['country'] = findRe(html, '<a href="/cg/avg.dll\?p=avg&sql=24:D\|\|\|206">(.*?)</')
@ -18,6 +17,11 @@ def getMovieData(allmovieId):
data['genre'] = parseList(html, 'Genre / Type') data['genre'] = parseList(html, 'Genre / Type')
data['keywords'] = parseList(html, 'Keywords') data['keywords'] = parseList(html, 'Keywords')
data['themes'] = parseList(html, 'Themes') data['themes'] = parseList(html, 'Themes')
data['boxoffice'] = parseEntry(html, 'Box office')[1:].replace(',', '')
data['produced'] = parseEntry(html, 'Produced by')
data['releasedate'] = parseEntry(html, 'Release')[0:10].replace(' ', '-')
data['released'] = parseEntry(html, 'Released by')
data['synopsis'] = stripTags(findRe(html, 'Plot Synopsis</td>.*?<td colspan="2"><p>(.*?)</td>'))
html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T1" % allmovieId) html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T1" % allmovieId)
data['review'] = stripTags(findRe(html, 'Review</td>.*?<td colspan="2"><p>(.*?)</td>')) data['review'] = stripTags(findRe(html, 'Review</td>.*?<td colspan="2"><p>(.*?)</td>'))
html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T2" % allmovieId) html = getUrlUnicode("http://www.allmovie.com/cg/avg.dll?p=avg&sql=1:%s~T2" % allmovieId)
@ -44,6 +48,9 @@ def getMoviePoster(allmovieId):
return data['poster'] return data['poster']
return '' return ''
def parseEntry(html, title):
return stripTags(findRe(html, '<span>%s</span>(.*?)</table>' % title))
def parseList(html, title): def parseList(html, title):
return map(lambda x: stripTags(x), findRe(html, '<span>%s</span>(.*?)</table>' % title).split('</li><li>')) return map(lambda x: stripTags(x), findRe(html, '<span>%s</span>(.*?)</table>' % title).split('</li><li>'))