def open_directory_data_insert():
"""
for inserting data after grabbing open directory
dbase used => pdfs.pdf
field: {added, keyword, title, url, snippet, thumb_updated, fpath}
1. downloading image
2. inserting data from fields
"""
if request.method == "POST":
added = datetime.datetime.now()
title = request.form["title"]
snippet = request.form["snippet"]
url = request.form["url"]
keyword = title
# insert database dengan 5 data di atas
pdfdb = c["pdfs"]
oid = pdfdb.pdf.insert({
"added": added,
"title": title,
"snippet": snippet,
"url": url,
"keyword": keyword,
})
print "sukses"
# buat folder path dulu
# simpan di folder dgn format => thn/bln/tanggal
# app folder
app_folder = os.getcwd()
# get year/month/date
date_folder = datetime.datetime.now().strftime("%Y/%m/%d")
# joined both
full_folder_path = os.path.join(app_folder, "assets", date_folder) # ~/path_to_app/assets/2014/11/09/fname.jpg
# create folder if not exists
if not os.path.exists(full_folder_path):
os.makedirs(full_folder_path)
img_filename = "%s-%s.png" % (oid, slugify(title))
# full file path
full_file_path = os.path.join(full_folder_path, img_filename)
# download the thumbnail
thumb_url = "http://docs.google.com/viewer?url=%s&a=bi&pagenumber=1&w=100" % url
imgstr = urllib2.urlopen(thumb_url).read()
with open(full_file_path, "w") as f:
f.write(imgstr)
# update database => 1. thumb_url: lokasi ke gambar 2. thumb_updated: terakhir update
# nanti di halaman index, tampilkan data yang ada thumb_updated saja
fpath = os.path.join(date_folder, img_filename)
pdfdb.pdf.update({"_id": ObjectId(oid)}, {"$set": {"fpath": fpath, "thumb_updated": datetime.datetime.now()}})
return "sukses"
def admin_single_url_inject():
"""
input: url path to pdf file
process: download thumbnail, add title, snippet and url, also keyword (optional)
post: input into database
perlukah pdfbox disini????
"""
if request.method == "POST":
added = datetime.datetime.now()
title = request.form["title"]
snippet = request.form["snippet"]
url = request.form["url"]
keyword = title
# insert database dengan 5 data di atas
pdfdb = c["pdfs"]
oid = pdfdb.pdf.insert({
"added": added,
"title": title,
"snippet": snippet,
"url": url,
"keyword": keyword,
})
# print "sukses"
# buat folder path dulu
# simpan di folder dgn format => thn/bln/tanggal
# app folder
app_folder = os.getcwd()
# get year/month/date
date_folder = datetime.datetime.now().strftime("%Y/%m/%d")
# joined both
full_folder_path = os.path.join(app_folder, "assets", date_folder) # ~/path_to_app/assets/2014/11/09/fname.jpg
# create folder if not exists
if not os.path.exists(full_folder_path):
os.makedirs(full_folder_path)
img_filename = "%s-%s.png" % (oid, slugify(title))
# full file path
full_file_path = os.path.join(full_folder_path, img_filename)
# download the thumbnail
thumb_url = "http://docs.google.com/viewer?url=%s&a=bi&pagenumber=1&w=100" % url
imgstr = urllib2.urlopen(thumb_url).read()
with open(full_file_path, "w") as f:
f.write(imgstr)
# update database => 1. thumb_url: lokasi ke gambar 2. thumb_updated: terakhir update
# nanti di halaman index, tampilkan data yang ada thumb_updated saja
fpath = os.path.join(date_folder, img_filename)
pdfdb.pdf.update({"_id": ObjectId(oid)}, {"$set": {"fpath": fpath, "thumb_updated": datetime.datetime.now()}})
return "sukses %s %s %s" % (url, title, snippet)
return render_template("admin/admin_inject_single_url.html")
def users_public_view(username):
""" this is for public view
contains:
all the picture uploaded.
"""
dbuser = c["entities"]
data = dbuser.users.find_one({"username": session.get("username")})
try:
favorites = dbuser.users.find_one({"username": username})["favorited"]
favorites = list(set(favorites)) # unique only
except:
favorites = []
# check if books have thumbnail, resouce? oid
pdfdb = c["pdfs"]
thumbs = []
images = []
titles = []
if favorites:
for i in favorites:
# get the data
datafavorites = pdfdb.pdf.find_one({"_id": ObjectId(i)})
# jika ada fpath (thumbnail tersedia)
if datafavorites.has_key("fpath"):
image_path = datafavorites["fpath"]
title = slugify(datafavorites["title"])
thumbs.append(True)
images.append(image_path)
titles.append(title)
else:
title = slugify(datafavorites["title"])
thumbs.append(False)
images.append("")
titles.append(title)
# zip it
favorites = zip(favorites, thumbs, images, titles)
# print favorites
return render_template("users/users_public_view.html", data=data, favorites=favorites, username=username)
def thumbnailer(term=None):
# data
docdb = c["pdfs"]
# randomize the skip
skip_number = random.randint(0, docdb.pdf.find().count() - 10)
data = docdb.pdf.find({"thumb_updated": {"$exists": False}}).skip(skip_number).limit(10)
# data = docdb.pdf.find().limit(10)
if term is not None:
# cari berdasarkan keyword $and berdasar thumb_updated == false
# pakai regex aja, sebenere yang lebih pas pake ful text, biar bisa search di-url juga :(
pattern = re.compile(".*" + term + ".*")
# data = docdb.pdf.find({"$and": [{"thumb_updated": {"$exists": False}}, {"title": pattern}]}).limit(10)
data = docdb.command("text", "pdf", search=term, limit=15)
data = [d["obj"] for d in data["results"] if "thumb_updated" not in d["obj"].viewkeys()] # harusnya cari yang belum ada field thumb_updated
if request.method == "POST":
oid = request.form["oid"]
url = request.form["url"]
title = request.form["title"]
# buat folder path dulu
# simpan di folder dgn format => thn/bln/tanggal
# app folder
app_folder = os.getcwd()
# get year/month/date
date_folder = datetime.datetime.now().strftime("%Y/%m/%d")
# joined both
full_folder_path = os.path.join(app_folder, "assets", date_folder) # ~/path_to_app/assets/2014/11/09/fname.jpg
# create folder if not exists
if not os.path.exists(full_folder_path):
os.makedirs(full_folder_path)
img_filename = "%s-%s.png" % (oid, slugify(title))
# full file path
full_file_path = os.path.join(full_folder_path, img_filename)
# download the thumbnail
imgstr = urllib2.urlopen(url).read()
with open(full_file_path, "w") as f:
f.write(imgstr)
# update database => 1. thumb_url: lokasi ke gambar 2. thumb_updated: terakhir update
# nanti di halaman index, tampilkan data yang ada thumb_updated saja
fpath = os.path.join(date_folder, img_filename)
docdb.pdf.update({"_id": ObjectId(oid)}, {"$set": {"added": datetime.datetime.now(), "fpath": fpath, "thumb_updated": datetime.datetime.now()}})
return "sukses %s %s" % (oid, url)
return render_template("admin/admin_thumbnailer.html", data=data)
def recent_feed():
# http://werkzeug.pocoo.org/docs/contrib/atom/
# wajibun: id(link) dan updated
feed = AtomFeed('Recent Articles',
feed_url = request.url, url=request.url_root)
data = [i[0] for i in col_term.get_range()][:100]
for d in data:
feed.add(
d,
content_type='text',
url = 'http://www.hotoid.com/berita/' + slugify(d),
updated = datetime.datetime.now(),
)
return feed.get_response()
def recent_feed():
# http://werkzeug.pocoo.org/docs/contrib/atom/
feed = AtomFeed('Recent Files',
feed_url = request.url, url=request.url_root)
data = db.freewaredata.find().sort("_id", -1).limit(100)
for d in data:
try:
feed.add(
d['title'],
d['description'],
content_type='text',
id=d['_id'],
url='http://www.blankons.com/'+slugify(onlychars(d['title']))+'/'+unicode(d['_id']),
updated=datetime.datetime.now(),
)
except:
feed.add(
d['title'],
content_type='text',
id=d['_id'],
url='http://www.blankons.com/'+slugify(onlychars(d['title']))+'/'+unicode(d['_id']),
updated=datetime.datetime.now(),
)
return feed.get_response()
def slug(s):
"""
transform words into slug
usage: {{ string|slug }}
"""
return slugify(s)
def redirect_search():
q = request.args.get('q')
return redirect("/" + slugify(q), 301)
def slug(s): return slugify(s)
def berita(topik):
topik = slugify(topik)
col_term.insert(unicode(topik.replace('-', ' ')), {'added': datetime.datetime.now(), 'hits': 1})
query = topik.replace('-', '+')
url1 = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&key=AIzaSyDgVEQ1PB5N4Q0YizPpyLdafL6FmgjdN1w&cx=002126600575969604992:lhhlw8muw00&gl=en&rsz=8&start=0&q=' + query + '+site:kompas.com'
url2 = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&key=AIzaSyDgVEQ1PB5N4Q0YizPpyLdafL6FmgjdN1w&cx=002126600575969604992:lhhlw8muw00&gl=en&rsz=8&start=0&q=' + query + '+site:detik.com'
url3 = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&key=AIzaSyDgVEQ1PB5N4Q0YizPpyLdafL6FmgjdN1w&cx=002126600575969604992:lhhlw8muw00&gl=en&rsz=8&start=0&q=' + query + '+site:viva.co.id'
url4 = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&key=AIzaSyDgVEQ1PB5N4Q0YizPpyLdafL6FmgjdN1w&cx=002126600575969604992:lhhlw8muw00&gl=en&rsz=8&start=0&q=' + query + '+site:kaskus.co.id'
url5 = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&key=AIzaSyDgVEQ1PB5N4Q0YizPpyLdafL6FmgjdN1w&cx=002126600575969604992:lhhlw8muw00&gl=en&rsz=8&start=0&q=' + query + '+site:merdeka.com'
url6 = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&key=AIzaSyDgVEQ1PB5N4Q0YizPpyLdafL6FmgjdN1w&cx=002126600575969604992:lhhlw8muw00&gl=en&rsz=8&start=0&q=' + query + '+site:republika.co.id'
#url6 = 'https://gdata.youtube.com/feeds/api/videos?q='+query+'&v=2&alt=jsonc'
try:
col_topic.get(topik)['kompas']
data1 = json.loads(col_topic.get(topik)['kompas'])
except:
response1 = urllib2.urlopen(url1).read()
col_topic.insert(topik, {'kompas': response1}, ttl=86400 * 7)
data1 = json.loads(col_topic.get(topik)['kompas'])
try:
col_topic.get(topik)['detik']
data2 = json.loads(col_topic.get(topik)['detik'])
except:
response2 = urllib2.urlopen(url2).read()
col_topic.insert(topik, {'detik': response2}, ttl=86400 * 7)
data2 = json.loads(col_topic.get(topik)['detik'])
try:
col_topic.get(topik)['vivanews']
data3 = json.loads(col_topic.get(topik)['vivanews'])
except:
response3 = urllib2.urlopen(url3).read()
col_topic.insert(topik, {'vivanews': response3}, ttl=86400 * 7)
data3 = json.loads(col_topic.get(topik)['vivanews'])
try:
col_topic.get(topik)['kaskus']
data4 = json.loads(col_topic.get(topik)['kaskus'])
except:
response4 = urllib2.urlopen(url4).read()
col_topic.insert(topik, {'kaskus': response4}, ttl=86400)
data4 = json.loads(col_topic.get(topik)['kaskus'])
try:
col_topic.get(topik)['merdeka']
data5 = json.loads(col_topic.get(topik)['merdeka'])
except:
response5 = urllib2.urlopen(url5).read()
col_topic.insert(topik, {'merdeka': response5}, ttl=86400 * 7)
data5 = json.loads(col_topic.get(topik)['merdeka'])
try:
col_topic.get(topik)['republika']
data6 = json.loads(col_topic.get(topik)['republika'])
except:
response6 = urllib2.urlopen(url6).read()
col_topic.insert(topik, {'republika': response6}, ttl=86400 * 7)
data6 = json.loads(col_topic.get(topik)['republika'])
return render_template("berita2.html", data1=data1, data2=data2, data3=data3, data4=data4, data5=data5, data6=data6, topik=topik)
def cari():
q = request.args.get('q')
return redirect("/berita/" + slugify(q), 301)
def music():
q = request.args.get('q')
return redirect("/"+slugify(q)+"/", 301)
def suggested_topics(tag):
"""
buat halaman tags yang isinya search term
dari onkeywords.com, adwords, ubersuggests dan sejenisnya
"""
# return redirect("/tag/" + tag)
pdfdb = c["pdfs"]
tagsdb = c["pdfterms"]
terms = c["terms"]
# prevent keyword injection
kwrd = tagsdb.term.find_one({"term": tag.replace("-", " ")})
if not kwrd:
return redirect("/", 302)
tag = tag.replace("-", " ")
data = pdfdb.command("text", "pdf", search=tag, limit=10)
results_count = data["stats"]["nscanned"]
# ini harusnya prioritas nyari yang ada thumbnailnya dulu
# piye carane yo????
data = [d["obj"] for d in data["results"]]
# building related data
related_data = terms.command("text", "term", search=tag, limit=10)
related_data = [d["obj"] for d in related_data["results"]]
## on-page seo
# 1. related tags for meta desc
meta_desc = ", ".join([d["term"] for d in related_data][:5])
# 2. meta keywords, ambil dari tag, split, join
meta_key = ", ".join([t for t in tag.split(" ") if len(t) > 3])
# 3. meta key tags with get rid off short word
meta_key_tags = [t for t in tag.split(" ")[:5] if len(t) > 3]
# 4. fake category?
meta_key_cat = tag.split(" ")[0]
# get tags suggestion to enrich index and strengthen onpage seo
tags = tagsdb.command("text", "term", search=tag)
tags = [d["obj"] for d in tags["results"]]
random.shuffle(tags)
tags = tags[:5]
# show h1 tags only for googlebot
# googlebot detection
refresher = False
print
print
print "referrer: %s" % request.headers
print "====" * 10
print request.headers.get("Referer")
# print request.headers.get("referrer")
print
print
# if 'Googlebot' in request.headers['User-Agent']:
try:
if 'google.com' in request.referrer:
refresher = True
# save setem, on file for now => setem.log
from urllib import unquote_plus
referer = request.headers.get("Referer")
pattern = re.compile(r"&q=(.*?)&")
setem = re.search(pattern, referer)
# print referer
if setem: # ada setem
setem = re.search(pattern, referer)
print setem.group(1)
# write to file
with open(os.path.join(os.getcwd(), "setem.log"), "a") as f:
if len(setem.group(1)) > 5: # remove nil setem
f.write(unquote_plus(setem.group(1)) + "\n")
####
# disini ini sekalian membuat halaman tag untuk kemudian
return redirect("/topic/" + slugify(tag))
# redirect ke tags yang asli, halman tag di kasih javascript code buat
# prevent back button
####
except:
pass
# users count
users_count = dbentity.users.find().count()
last_user = [i for i in dbentity.users.find()][-1]
return render_template("topics.html", data=data, tag=tag, results_count=results_count,
related_data=related_data, tags=tags, meta_desc=meta_desc,
meta_key=meta_key, meta_key_tags=meta_key_tags, meta_key_cat=meta_key_cat,
refresher=refresher, users_count=users_count, last_user=last_user)
def music():
q = request.args.get('q')
db.terms2.insert({'query': q.replace('-', ' ')})
return redirect("/"+slugify(q)+"/", 301)
