index +search info

archive.py

@@ -15,7 +15,7 @@ def run(args):
     i = 0
     for u in args.url:
         name = args.names[i] if i < len(args.names) else None
-        lists.crawl.crawl(u, name, args.arch)
+        lists.crawl.crawl(url=u, name=name, sublist_name=name, archive_dir=args.arch) #<-- sublist for nettime
         i = i + 1
     
     sys.exit()

lists/crawl.py

@@ -26,7 +26,9 @@ def crawl(url, name, sublist_name=None, archive_dir="archives"):
 	# special case -- nettime.
 	# the name should be the sublist_name (i.e nettime-l)
 	elif "nettime" in name:
-		mhonarc_nettime.collect_from_url(url, name, name, archive_dir)
+		if sublist_name is None:
+			sublist_name = name
+		mhonarc_nettime.collect_from_url(url, name, sublist_name, archive_dir)
 
 	else:
 		print('mhonarc?')

lists/mhonarc_nettime.py

@@ -26,17 +26,20 @@ def collect_from_url(url, name, sublist_name, base_archive_dir="archives", mbox=
 	threads = []
 	lists = soup.select('ul:nth-of-type(2) li')    
 
+
 	for l in lists:
 
 		if l.strong is None:
 			continue
 
 		name = l.strong.string
+		print(name + " - " + sublist_name)
 
 		if name.lower() == sublist_name.lower():
 
 			threads_url_list = []
 			threads_links = l.select('ul li a')
+
 			for t in threads_links:
 				thread_url = urllib.parse.urljoin(base_url, t.get('href'))
 				threads_url_list.append(thread_url)
@@ -79,6 +82,10 @@ def collect_threads_from_url(url, base_archive_dir, mbox=False):
 	base_url = url
 
 	# collect name
+
+	e = soup.select('p:nth-of-type(1) title')
+	print(soup)
+
 	threads_name = soup.select('p:nth-of-type(1) title')[0].string
 	threads_name = threads_name.replace(' ', '_')
 

www/archives.py

@@ -1,79 +0,0 @@
-import logging, os, json
-import search.archive
-
-class Singleton(type):
-    _instances = {}
-    def __call__(cls, *args, **kwargs):
-        if cls not in cls._instances:
-            cls._instances[cls] = super(Singleton, cls).__call__(*args, **kwargs)
-            logging.info('**** new Singleton instance')
-        return cls._instances[cls]
-
-class Archives(metaclass=Singleton):
-
-	def __init__(self, archives_dir=None):
-
-		if archives_dir==None:
-			from www import config
-			self.archives_dir = config.ARCHIVES_PATH
-		else:
-			self.archives_dir = archives_dir
-
-		self.data = {}
-		self.loaded = False
-
-		logging.info('loading archives...')
-
-		self.load()
-
-		logging.info('done.')
-
-	def load(self):
-
-		if self.loaded:
-			return
-
-		if not os.path.isdir(self.archives_dir):
-			logging.error("Archives:: the path - " + self.archives_dir + " - is not a valid directory. Aborting.")
-			logging.error(" -- current cwd is: " + os.getcwd())
-
-			return
-
-		arch = [d for d in os.listdir(self.archives_dir) if os.path.isdir(os.path.join(self.archives_dir, d))]
-
-		self.data = {}
-		for a in arch:
-
-			logging.info("loading " + a)
-
-			# archive_path = os.path.join(self.archives_dir, a)
-			self.data[a] = self.load_archive(self.archives_dir, a)
-
-			logging.info("done.")
-
-		self.loaded = True
-		
-
-	def load_archive(self, archive_dir, archive_name):
-
-		if not os.path.isdir(archive_dir):
-			logging.error("Archives:: the path - " + archive_dir + " - is not a valid directory. Aborting.")
-			return
-
-		archive = search.archive.Archive(archive_dir)
-		archive.load(archive_name)
-		return archive
-
-		# # -- shoudl use Archive in searh module here....
-
-		# files = [f for f in os.listdir(archive_dir) if f.endswith('.json')]
-
-		# arch = {}
-		# for f in files:
-		# 	file_path = os.path.join(archive_dir, f)
-		# 	with open(file_path) as fdata:
-		# 		arch[f.replace('.json', '')] = json.load(fdata)
-
-		# return arch	
-
-

www/routes.py

@@ -11,6 +11,11 @@ import logging
 def index():
 	return render_template("index.html")
 
+@app.route('/favicon.ico')
+def favicon():
+    return send_from_directory(os.path.join(app.root_path, 'static'),
+                               'favicon.ico', mimetype='image/vnd.microsoft.icon')	
+
 @app.route('/search')
 def searh():
 	

www/static/ooo.js

@@ -0,0 +1,17 @@
+var c = 255
+var x = 0
+function b() {
+	c -= 1;
+	document.body.style.backgroundColor = 'rgb(' + c + ',' + c + ',' + c + ')';
+}
+function m() {
+	x += 0.7
+	s = document.getElementById('search');
+	s.style.left = x + 'px'
+	s.style.top = x + 'px'
+}
+window.onload = function () {
+	// setInterval(b, 500);
+	setInterval(m, 200);
+};
+

www/static/search.js

@@ -2,6 +2,11 @@
 $(document).ready(function(){
 	$('#loading').hide()
 
+	$('#info').click( function() {
+		console.log("click");
+		$('#info-search').toggle();
+	});
+
 	$('#search').submit(function(e) {
 		e.preventDefault();
 		args = $(this).serialize();	
@@ -38,7 +43,7 @@ function search_result_archive(a) {
 		
 		$.each(r.hits, function(j, h){
 			// console.log(h)
-			let hit = '<li><a href="' + h.url+ '">' + h.subject + '</a> -- <i>' + h.author_name + '</i></li>';
+			let hit = '<li><a href="' + h.url+ '" target="_blank">' + h.subject + '</a> -- <i>' + h.author_name + '</i></li>';
 			hits += hit;
 		});
 		hits += "</ul>";

www/templates/index.html

@@ -1,6 +1,11 @@
 <html>
-<head></head>
+<head>
-<body>
+	<title>Times of Nettime</title>
-	 <a href="/search"><h3>---> SEARCH <---</h3></a>
+	<script type="text/javascript" src="{{ url_for('static',filename='ooo.js') }}"></script>
+</head>
+<body bgcolor="blue">
+	<div id="search" style="position: absolute;">
+		<a href="/search"><h3><img src="{{ url_for('static',filename='CYBERPLA.GIF') }}" width="150"></h3></a>
+	</div>	 
 </body>
 </html>

www/templates/search.html

@@ -1,5 +1,6 @@
 <html>
 <head>
+	<title>Times of Nettime</title>
 	<link rel="stylesheet" type="text/css" href="{{ url_for('static',filename='c3.min.css') }}">
 	<script type=text/javascript src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.2.1/jquery.min.js"></script>
 	<script type="text/javascript" src="{{ url_for('static',filename='d3.min.js') }}" charset="utf-8"></script>
@@ -21,8 +22,21 @@
 			 {% endfor %}
 		</select>		
 		<input type="submit" value="search" id="submit">
+		<input type="button" value=" ? " id="info">
 		<div id="loading">Loading...</div>
 	</form>
+	<div id="info-search" style="display: none">
+		<table><tbody><tr><th>Operator</th><th>   </th></tr>
+		<tr><td>+</td><td>The word is mandatory in all text returned.</td></tr>
+		<tr><td>-</td><td>The word cannot appear in any text returned.</td></tr>
+		<tr><td>&lt;</td><td>The word that follows has a lower relevance than other words, although text containing it will still match</td></tr>
+		<tr><td>&gt;</td><td>The word that follows has a higher relevance than other words.</td></tr>
+		<tr><td>()</td><td>Used to group words into subexpressions.</td></tr>
+		<tr><td>~</td><td>The word following contributes negatively to the relevance of the text (which is different to the '-' operator, which specifically excludes the word, or the '&lt;' operator, which still causes the word to contribute positively to the relevance of the text.</td></tr>
+		<tr><td>*</td><td>The wildcard, indicating zero or more characters. It can only appear at the end of a word.</td></tr>
+		<tr><td>"</td><td>Anything enclosed in the double quotes is taken as a whole (so you can match phrases, for example).</td></tr>
+		</tbody></table>				
+	</div>
 	<div id="graph"></div>
 	<div id="results"></div>
 </body>