python-oxweb/ox/itunes.py

179 lines
6.8 KiB
Python
Raw Normal View History

2008-04-29 13:08:23 +00:00
import re
import urllib
from oxutils.cache import getUrl
2008-05-07 08:15:25 +00:00
from oxutils.html import decodeHtml, stripTags
from oxutils.text import findRe
2008-04-29 13:08:23 +00:00
from oxutils.text import findString
# to sniff itunes traffic, use something like
# sudo tcpdump -i en1 -Avs 8192 host appleglobal.112.2o7.net
2008-05-07 11:29:00 +00:00
# http://ax.phobos.apple.com.edgesuite.net/WebObjects/MZSearch.woa/wa/advancedSearch?media=music&songTerm=&genreIndex=1&flavor=0&mediaType=2&composerTerm=&allArtistNames=Arcadia&ringtone=0&searchButton=submit
# http://ax.phobos.apple.com.edgesuite.net/WebObjects/MZSearch.woa/wa/advancedSearch?media=movie&movieTerm=The%20Matrix&descriptionTerm=&ratingIndex=1&mediaType=3&directorProducerName=Andy%20Wachowski&flavor=0&releaseYearTerm=1999&closedCaption=0&actorTerm=&searchButton=submit
2008-04-29 13:08:23 +00:00
ITUNES_HEADERS = {
'X-Apple-Tz': '0',
'X-Apple-Storefront': '143441-1',
'User-Agent': 'iTunes/7.6.2 (Macintosh; U; Intel Mac OS X 10.5.2)',
'Accept-Language': 'en-us, en;q=0.50',
'Accept-Encoding': 'gzip',
'Connection': 'close',
}
def composeUrl(request, parameters):
if request == 'advancedSearch':
2008-05-07 11:29:00 +00:00
url = 'http://ax.phobos.apple.com.edgesuite.net/WebObjects/MZSearch.woa/wa/advancedSearch?'
if parameters['media'] == 'music':
url += urllib.urlencode({
'albumTerm': parameters['title'],
'allArtistNames': parameters['artist'],
'composerTerm': '',
'flavor': 0,
'genreIndex': 1,
'media': 'music',
'mediaType': 2,
'ringtone': 0,
'searchButton': 'submit',
'songTerm': ''
})
elif parameters['media'] == 'movie':
url += urllib.urlencode({
'actorTerm': '',
'closedCaption': 0,
'descriptionTerm': '',
'directorProducerName': parameters['director'],
'flavor': 0,
'media': 'movie',
'mediaType': 3,
'movieTerm': parameters['title'],
'ratingIndex': 1,
'releaseYearTerm': '',
'searchButton': 'submit'
})
2008-04-29 13:08:23 +00:00
elif request == 'viewAlbum':
url = 'http://phobos.apple.com/WebObjects/MZStore.woa/wa/viewAlbum?id=%s' % parameters['id']
2008-05-07 11:29:00 +00:00
elif request == 'viewMovie':
2008-05-07 11:54:37 +00:00
url = 'http://phobos.apple.com/WebObjects/MZStore.woa/wa/viewMovie?id=%s&prvw=1' % parameters['id']
2008-04-29 13:08:23 +00:00
return url
def parseXmlDict(xml):
values = {}
strings = xml.split('<key>')
for string in strings:
if string.find('</key>') != -1:
2008-05-07 08:15:25 +00:00
key = findRe(string, '(.*?)</key>')
type = findRe(string, '</key><(.*?)>')
2008-04-29 13:08:23 +00:00
if type == 'true/':
value = True
else:
2008-05-07 08:15:25 +00:00
value = findRe(string, '<%s>(.*?)</%s>' % (type, type))
2008-04-29 13:08:23 +00:00
if type == 'integer':
value = int(value)
elif type == 'string':
2008-05-07 08:15:25 +00:00
value = decodeHtml(value)
2008-04-29 13:08:23 +00:00
values[key] = value
return values
2008-05-07 11:29:00 +00:00
def parseCast(xml, title):
list = []
try:
strings = findRe(xml, '<SetFontStyle normalStyle="textColor">%s(.*?)</VBoxView>' % title[:-1].upper()).split('</GotoURL>')
strings.pop()
for string in strings:
list.append(findRe(string, '<SetFontStyle normalStyle="textColor">(.*?)</SetFontStyle>'))
return list
except:
return list
def parseMovies(xml, title):
list = []
strings = findRe(xml, '<SetFontStyle normalStyle="outlineTitleFontStyle"><b>%s(.*?)</Test>' % title[:-1].upper()).split('</GotoURL>')
strings.pop()
for string in strings:
list.append({
'id': findRe(string, 'viewMovie\?id=(.*?)&'),
'title': findRe(string, '<SetFontStyle normalStyle="outlineTextFontStyle"><b>(.*?)</b></SetFontStyle>')
})
return list
2008-04-29 13:08:23 +00:00
class ItunesAlbum:
2008-05-07 11:29:00 +00:00
def __init__(self, id = '', title = '', artist = ''):
self.id = id
2008-04-29 13:08:23 +00:00
self.title = title
self.artist = artist
2008-05-07 11:29:00 +00:00
if not id:
self.id = self.getId()
2008-04-29 13:08:23 +00:00
def getId(self):
2008-05-07 11:29:00 +00:00
url = composeUrl('advancedSearch', {'media': 'music', 'title': self.title, 'artist': self.artist})
xml = getUrl(url, headers = ITUNES_HEADERS)
2008-05-07 08:15:25 +00:00
id = findRe(xml, 'viewAlbum\?id=(.*?)&')
2008-04-29 13:08:23 +00:00
return id
def getData(self):
data = {'id': self.id}
url = composeUrl('viewAlbum', {'id': self.id})
xml = getUrl(url, None, ITUNES_HEADERS)
2008-05-07 08:15:25 +00:00
data['albumName'] = findRe(xml, '<B>(.*?)</B>')
data['artistName'] = findRe(xml, '<b>(.*?)</b>')
2008-05-07 11:29:00 +00:00
data['coverUrl'] = findRe(xml, 'reflection="." url="(.*?)"')
2008-05-07 08:15:25 +00:00
data['genre'] = findRe(xml, 'Genre:(.*?)<')
data['releaseDate'] = findRe(xml, 'Released(.*?)<')
data['review'] = stripTags(findRe(xml, 'REVIEW</b>.*?<SetFontStyle normalStyle="textColor">(.*?)</SetFontStyle>'))
2008-04-29 13:08:23 +00:00
data['tracks'] = []
2008-05-07 08:15:25 +00:00
strings = findRe(xml, '<key>items</key>.*?<dict>(.*?)$').split('<dict>')
2008-04-29 13:08:23 +00:00
for string in strings:
2008-05-07 08:15:25 +00:00
data['tracks'].append(parseXmlDict(string))
data['type'] = findRe(xml, '<key>listType</key><string>(.*?)<')
2008-04-29 13:08:23 +00:00
return data
2008-05-07 11:29:00 +00:00
class ItunesMovie:
def __init__(self, id = '', title = '', director = ''):
self.id = id
self.title = title
self.director = director
if not id:
self.id = self.getId()
def getId(self):
url = composeUrl('advancedSearch', {'media': 'movie', 'title': self.title, 'director': self.director})
xml = getUrl(url, headers = ITUNES_HEADERS)
id = findRe(xml, 'viewMovie\?id=(.*?)&')
return id
def getData(self):
data = {'id': self.id}
url = composeUrl('viewMovie', {'id': self.id})
xml = getUrl(url, None, ITUNES_HEADERS)
2008-05-07 11:54:37 +00:00
f = open('/Users/rolux/Desktop/iTunesData.xml', 'w')
f.write(xml)
f.close()
2008-05-07 11:29:00 +00:00
data['actors'] = parseCast(xml, 'actors')
string = findRe(xml, 'Average Rating:(.*?)</HBoxView>')
data['averageRating'] = string.count('rating_star_000033.png') + string.count('&#189;') * 0.5
data['directors'] = parseCast(xml, 'directors')
data['format'] = findRe(xml, 'Format:(.*?)<')
data['genre'] = decodeHtml(findRe(xml, 'Genre:(.*?)<'))
data['plotSummary'] = decodeHtml(findRe(xml, 'PLOT SUMMARY</b>.*?<SetFontStyle normalStyle="textColor">(.*?)</SetFontStyle>'))
data['posterUrl'] = findRe(xml, 'reflection="." url="(.*?)"')
data['producers'] = parseCast(xml, 'producers')
data['rated'] = findRe(xml, 'Rated(.*?)<')
data['relatedMovies'] = parseMovies(xml, 'related movies')
data['releaseDate'] = findRe(xml, 'Released(.*?)<')
data['runTime'] = findRe(xml, 'Run Time:(.*?)<')
data['screenwriters'] = parseCast(xml, 'screenwriters')
data['soundtrackId'] = findRe(xml, 'viewAlbum\?id=(.*?)&')
2008-05-07 11:54:37 +00:00
data['trailerUrl'] = findRe(xml, 'autoplay="." url="(.*?)"')
2008-05-07 11:29:00 +00:00
return data
2008-04-29 13:16:51 +00:00
if __name__ == '__main__':
2008-05-07 08:15:25 +00:00
import simplejson
2008-05-07 11:29:00 +00:00
data = ItunesAlbum(title = 'So Red the Rose', artist = 'Arcadia').getData()
print simplejson.dumps(data, sort_keys = True, indent = 4)
data = ItunesMovie(title = 'The Matrix', director = 'Wachowski').getData()
2008-05-07 08:15:25 +00:00
print simplejson.dumps(data, sort_keys = True, indent = 4)
2008-05-07 11:29:00 +00:00
for v in data['relatedMovies']:
data = ItunesMovie(id = v['id']).getData()
print simplejson.dumps(data, sort_keys = True, indent = 4)
2008-05-07 08:15:25 +00:00
# print test.getData()