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

add parser for trailers.apple.com

Browse source
This commit is contained in:
rolux 2011-07-30 10:12:24 +02:00
parent faeed07934
commit 9c5f5097c7
1 changed files with 32 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
ox/web/apple.py
View file

@ -1,3 +1,4 @@
import json
import re import re
from ox.cache import readUrlUnicode from ox.cache import readUrlUnicode
@ -10,9 +11,12 @@ HEADERS = {
'X-Apple-Tz': '7200', 'X-Apple-Tz': '7200',
'Accept-Encoding': 'gzip, deflate' 'Accept-Encoding': 'gzip, deflate'
} }
USER_AGENT = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7) '
USER_AGENT += 'AppleWebKit/534.48.3 (KHTML, like Gecko) Version/5.1 Safari/534.48.3'
def getMovieData(title, director): def getMovieData(title, director):
data = None data = {}
# itunes section (preferred source for link)
url = 'http://ax.search.itunes.apple.com/WebObjects/MZSearch.woa/wa/advancedSearch' url = 'http://ax.search.itunes.apple.com/WebObjects/MZSearch.woa/wa/advancedSearch'
url += '?media=movie&movieTerm=' + title url += '?media=movie&movieTerm=' + title
url += '&actorNames=&directorProducerName=' + director url += '&actorNames=&directorProducerName=' + director
@ -23,17 +27,37 @@ def getMovieData(title, director):
regexp += '<img width=".*?" height=".*?" alt=".*?" class="artwork" src="(.*?)" /></div></a>' regexp += '<img width=".*?" height=".*?" alt=".*?" class="artwork" src="(.*?)" /></div></a>'
results = re.compile(regexp).findall(html) results = re.compile(regexp).findall(html)
if results: if results:
data = { data['link'] = results[0][0]
'link': results[0][0], data['poster'] = results[0][1].replace('140x140', '600x600')
'poster': results[0][1].replace('140x140', '600x600')
}
html = readUrlUnicode(data['link'], headers=HEADERS) html = readUrlUnicode(data['link'], headers=HEADERS)
regexp = 'video-preview-url="(.*?)"' results = re.compile('video-preview-url="(.*?)"').findall(html)
results = re.compile(regexp).findall(html)
if results: if results:
data['trailer'] = results[0] data['trailer'] = results[0]
# trailers section (preferred source for poster and trailer)
host = 'http://trailers.apple.com'
url = host + '/trailers/home/scripts/quickfind.php?callback=searchCallback&q=' + title
js = json.loads(readUrlUnicode(url)[16:-4])
results = js['results']
if results:
url = host + results[0]['location']
if not 'link' in data:
data['link'] = url
headers = {
'User-Agent': USER_AGENT
}
html = readUrlUnicode(url, headers=headers)
results = re.compile('"(' + host + '.*?poster\.jpg)"').findall(html)
if results:
data['poster'] = results[0].replace('poster.jpg', 'poster-xlarge.jpg')
html = readUrlUnicode(url + 'includes/playlists/web.inc', headers=headers)
results = re.compile('"(' + host + '\S+\.mov)"').findall(html)
if results:
data['trailer'] = results[-1]
return data return data
if __name__ == '__main__': if __name__ == '__main__':
print getMovieData('Alphaville', 'Jean-Luc Godard') print getMovieData('Alphaville', 'Jean-Luc Godard')
print getMovieData('Sin City', 'Roberto Rodriguez') print getMovieData('Sin City', 'Roberto Rodriguez')
print getMovieData('Breathless', 'Jean-Luc Godard')
print getMovieData('Capitalism: A Love Story', 'Michael Moore')
print getMovieData('Film Socialisme', 'Jean-Luc Godard')