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

ox.web under_score api rewrite

Browse source
This commit is contained in:
j 2012-08-15 17:15:40 +02:00
commit a4fd3c930f
29 changed files with 268 additions and 285 deletions
Download patch file Download diff file Expand all files Collapse all files

22
ox/web/movieposterdb.py
View file

@ -6,39 +6,39 @@ import re
from ox.cache import read_url
from ox import find_re
def getData(id):
def get_data(id):
'''
>>> getData('0060304')['posters'][0]
>>> get_data('0060304')['posters'][0]
u'http://www.movieposterdb.com/posters/06_03/1967/0060304/l_99688_0060304_639fdd1e.jpg'
>>> getData('0123456')['posters']
>>> get_data('0123456')['posters']
[]
'''
data = {
"url": getUrl(id)
"url": get_url(id)
}
data["posters"] = getPostersByUrl(data["url"])
data["posters"] = get_posters(data["url"])
return data
def getId(url):
def get_id(url):
return url.split("/")[-2]
def getPostersByUrl(url, group=True, timeout=-1):
def get_posters(url, group=True, timeout=-1):
posters = []
html = read_url(url, timeout=timeout, unicode=True)
if url in html:
if group:
results = re.compile('<a href="(http://www.movieposterdb.com/group/.+?)\??">', re.DOTALL).findall(html)
for result in results:
posters += getPostersByUrl(result, False)
posters += get_posters(result, False)
results = re.compile('<a href="(http://www.movieposterdb.com/poster/.+?)">', re.DOTALL).findall(html)
for result in results:
html = read_url(result, timeout=timeout, unicode=True)
posters.append(find_re(html, '"(http://www.movieposterdb.com/posters/.+?\.jpg)"'))
return posters
def getUrl(id):
def get_url(id):
return "http://www.movieposterdb.com/movie/%s/" % id
if __name__ == '__main__':
print getData('0060304')
print getData('0133093')
print get_data('0060304')
print get_data('0133093')