embedder/__init__.py
Code: [Select]
embedder/_list.py
Code: [Select]
I studied the links from (& only from) http://embed.ly/providers :eheh: Great thing about re in python is that it's allows named groups, much better than counting the groups.
embedder/youtube.py
Code: [Select]
All of the modules were very easy to code because the urls had id's in them, except revision3 that required HTML DOM, just to get the id from meta tag. Also I had to use database caching for revision3 because HTML DOM is damn slow. It's took about two hours to get revision3 to work.
embedder/revision3.py
Code: [Select]
As you can see each module has it's own template (or html code). I can't believe how most of it was ridiculously easy in Python.
import re
from importlib import import_module
from _lib.shortcode import shortcode
from ._list import __embedlist
def execute(user, url):
msg = ''
for list in __embedlist:
match = re.match(list['re'], url, flags=re.I)
if match:
try:
module = import_module('_lib.embedder.' + list['module'])
return module.execute(user, match, 640, 376)
except:
msg = "\nModule Failed to load"
url = "[url]" + url + "[/url]" + msg
code = shortcode(user=user, filter=['url'])
url = code.execute(url)
return urlembedder/_list.py
__embedlist = [
{
're': '^http(s?)://([a-z]*).youtube.com/(watch|index)\?(.*)v=(?P<youtubeid>[a-zA-Z0-9]+)',
'module': 'youtube'
},
{
're': '^http(s?)://([a-z]*).youtube.com/v/(?P<youtubeid>[a-zA-Z0-9]+)',
'module': 'youtube'
},
{
're': '^http(s?)://youtu.be/(?P<youtubeid>[a-zA-Z0-9]+)',
'module': 'youtube'
},
{
're': '^http(s?)://www.metacafe.com/watch/(?P<metacafeid>\d+)/(?P<metacafename>[a-zA-Z0-9_-]+)(/?)',
'module': 'metacafe'
},
{
're': '^http(s?)://www.dailymotion.com/(.*)video/(?P<dailymotionid>[^_]+)',
'module': 'dailymotion'
},
{
're': '^http(s?)://www.gametrailers.com/video/(?P<gametrailersname>[a-zA-Z-]+)/(?P<gametrailersid>\d+)(/?)',
'module': 'gametrailers'
},
{
're': '^http(s?)://([www.]?)collegehumor.com/video/(?P<collegehumorid>\d+)(/?)',
'module': 'collegehumor'
},
{
're': '^http(s?)://www.funnyordie.com/videos/(?P<funnyordieid>[a-zA-Z0-9]+)(/?)',
'module': 'funnyordie'
},
{
're': '^http(s?)://revision3.com/(?P<r3group>[a-zA-Z0-9]+)/(?P<r3title>[a-zA-Z0-9]+)(/?)',
'module': 'revision3'
},
{
're': '^http(s?)://www.break.com/([a-zA-Z-]+)/(?P<breakname>[a-zA-Z-]+)-(?P<breakid>\d+)(/?)',
'module': 'break'
},
]
I studied the links from (& only from) http://embed.ly/providers :eheh: Great thing about re in python is that it's allows named groups, much better than counting the groups.
embedder/youtube.py
from django.template import Context, loader
def execute(user, match, width, height):
youtubeid = match.group('youtubeid')
template = loader.get_template('embedder/youtube.html')
context = Context({
'youtubeid': youtubeid, 'width': width, 'height': height
})
return template.render(context)
All of the modules were very easy to code because the urls had id's in them, except revision3 that required HTML DOM, just to get the id from meta tag. Also I had to use database caching for revision3 because HTML DOM is damn slow. It's took about two hours to get revision3 to work.
embedder/revision3.py
from django.template import Context, loader
import hashlib
import json
from embed_cache.models import embed_cache
import urllib2
import html5lib
from html5lib import treebuilders
import re
def execute(user, match, width, height):
r3group = match.group('r3group')
r3title = match.group('r3title')
prehash = "revision3/" + r3group + "/" + r3title
hash = hashlib.new('ripemd160')
hash.update(prehash)
hash = hash.hexdigest()
try:
object = embed_cache.objects.get(hash=hash)
data = json.loads(object.data)
r3id = data['r3id']
del data
del object
except:
try:
parser = html5lib.HTMLParser(tree=treebuilders.getTreeBuilder("dom"))
dom = parser.parse(urllib2.urlopen(match.group(0)).read())
for node in dom.getElementsByTagName('meta'):
if node.getAttribute('property') == 'og:video':
content = node.getAttribute('content')
break
pattern = 'http://revision3.com/player-v(?P<theid>[0-9]+)'
match2 = re.match(pattern, content, flags=re.I)
if match2:
r3id = match2.group('theid')
data = {'r3id': r3id}
data = json.dumps(data)
object = embed_cache.objects.create(hash=hash, data=data)
del object
del data
else:
return ""
except:
return ""
template = loader.get_template('embedder/revision3.html')
context = Context({
'r3id': r3id, 'width': width, 'height': height
})
return template.render(context)As you can see each module has it's own template (or html code). I can't believe how most of it was ridiculously easy in Python.
