gauthiier/listservs
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

index +search info

Browse Source
This commit is contained in:
gauthiier 2019-07-17 12:55:47 +02:00
parent f06a720e55
commit 07a026e93f
12 changed files with 186 additions and 210 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
archive.py
View File

@ -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()

4
lists/crawl.py
View File

@ -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?')

257
lists/mhonarc_nettime.py
View File

@ -6,125 +6,132 @@ DELAY = 0.2
def collect_from_url(url, name, sublist_name, base_archive_dir="archives", mbox=False):
response = urllib.request.urlopen(url)
html = response.read()
soup = BeautifulSoup(html, "html5lib")
response = urllib.request.urlopen(url)
html = response.read()
soup = BeautifulSoup(html, "html5lib")
# base url
base_url = soup.select('body p:nth-of-type(2) base')[0].get('href')
# base url
base_url = soup.select('body p:nth-of-type(2) base')[0].get('href')
#collect name
list_name = soup.select('body p:nth-of-type(2) title')[0].string
logging.info("Getting " + list_name + " list archive for " + sublist_name)
list_name = soup.select('body p:nth-of-type(2) title')[0].string
logging.info("Getting " + list_name + " list archive for " + sublist_name)
# create (main) directory
# this is where all temp files will be created
d = os.path.join(base_archive_dir, name)
if not os.path.exists(d):
os.makedirs(d)
# create (main) directory
# this is where all temp files will be created
d = os.path.join(base_archive_dir, name)
if not os.path.exists(d):
os.makedirs(d)
threads = []
lists = soup.select('ul:nth-of-type(2) li')
threads = []
lists = soup.select('ul:nth-of-type(2) li')
for l in lists:
if l.strong is None:
continue
for l in lists:
name = l.strong.string
if l.strong is None:
continue
if name.lower() == sublist_name.lower():
name = l.strong.string
print(name + " - " + sublist_name)
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)
if name.lower() == sublist_name.lower():
nbr_threads = str(len(threads_url_list))
n = 0
threads_url_list = []
threads_links = l.select('ul li a')
for u in threads_url_list:
time.sleep(DELAY)
n += 1
logging.info("## " + str(n) + " / " + nbr_threads + " ##")
try:
threads.append(collect_threads_from_url(u, base_archive_dir=d, mbox=mbox))
except KeyboardInterrupt:
sys.exit(0)
except:
logging.warning("Error archiving: " + l[1] + "... Continuing.")
ex_t, ex, tb = sys.exc_info()
print(ex_t)
traceback.print_tb(tb)
del tb
continue
for t in threads_links:
thread_url = urllib.parse.urljoin(base_url, t.get('href'))
threads_url_list.append(thread_url)
return threads
nbr_threads = str(len(threads_url_list))
n = 0
# for u in threads_url_list[0:10]:
# print "---------------------------------------"
# tt = collect_threads_from_url(u, base_archive_dir, mbox)
# threads.append(tt)
for u in threads_url_list:
time.sleep(DELAY)
n += 1
logging.info("## " + str(n) + " / " + nbr_threads + " ##")
try:
threads.append(collect_threads_from_url(u, base_archive_dir=d, mbox=mbox))
except KeyboardInterrupt:
sys.exit(0)
except:
logging.warning("Error archiving: " + l[1] + "... Continuing.")
ex_t, ex, tb = sys.exc_info()
print(ex_t)
traceback.print_tb(tb)
del tb
continue
return None
return threads
# for u in threads_url_list[0:10]:
# print "---------------------------------------"
# tt = collect_threads_from_url(u, base_archive_dir, mbox)
# threads.append(tt)
return None
def collect_threads_from_url(url, base_archive_dir, mbox=False):
response = urllib.request.urlopen(url)
html = response.read()
soup = BeautifulSoup(html, "html5lib")
response = urllib.request.urlopen(url)
html = response.read()
soup = BeautifulSoup(html, "html5lib")
# base url
base_url = url
# base url
base_url = url
# collect name
threads_name = soup.select('p:nth-of-type(1) title')[0].string
threads_name = threads_name.replace(' ', '_')
# collect name
# thread data struct
threads = {'name' : threads_name, 'url' : base_url, 'threads' : []}
e = soup.select('p:nth-of-type(1) title')
print(soup)
logging.info("Collecting Threads of: " + threads_name)
threads_name = soup.select('p:nth-of-type(1) title')[0].string
threads_name = threads_name.replace(' ', '_')
# check if archive already exists
file_path = os.path.join(base_archive_dir, threads['name'] + ".json")
if os.path.isfile(file_path):
logging.info("archive already exists. loading from file " + file_path)
with open(file_path, 'r') as fpin:
threads = json.load(fpin)
else:
lists = soup.select('ul:nth-of-type(1) > li')
# thread data struct
threads = {'name' : threads_name, 'url' : base_url, 'threads' : []}
nbr_threads = str(len(lists))
n = 0
logging.info("Collecting Threads of: " + threads_name)
for l in lists:
n += 1
logging.info("> " + str(n) + " / " + nbr_threads)
# check if archive already exists
file_path = os.path.join(base_archive_dir, threads['name'] + ".json")
if os.path.isfile(file_path):
logging.info("archive already exists. loading from file " + file_path)
with open(file_path, 'r') as fpin:
threads = json.load(fpin)
else:
lists = soup.select('ul:nth-of-type(1) > li')
try:
thread = archive_thread(l, base_url, None)
threads['threads'].append(thread)
except:
ex_type, ex, tb = sys.exc_info()
traceback.print_tb(tb)
del tb
continue
nbr_threads = str(len(lists))
n = 0
time.sleep(DELAY)
for l in lists:
n += 1
logging.info("> " + str(n) + " / " + nbr_threads)
# write
logging.info("writing archive to file " + file_path)
try:
thread = archive_thread(l, base_url, None)
threads['threads'].append(thread)
except:
ex_type, ex, tb = sys.exc_info()
traceback.print_tb(tb)
del tb
continue
with open(file_path, 'w') as fp:
json.dump(threads, fp, indent=4)
time.sleep(DELAY)
logging.info("done. ")
# write
logging.info("writing archive to file " + file_path)
return threads
with open(file_path, 'w') as fp:
json.dump(threads, fp, indent=4)
logging.info("done. ")
return threads
def archive_thread(li, base_url, parent_thread_data):
@ -158,57 +165,57 @@ def archive_thread(li, base_url, parent_thread_data):
def collect_message(url, message):
response = urllib.request.urlopen(url)
html = response.read().decode(encoding="utf-8")
# html = response.read()
soup = BeautifulSoup(html, "html5lib")
response = urllib.request.urlopen(url)
html = response.read().decode(encoding="utf-8")
# html = response.read()
soup = BeautifulSoup(html, "html5lib")
#note: this should follow an RFC header standard -- MHonArc has header info in the 1th <pre>
#note: this should follow an RFC header standard -- MHonArc has header info in the 1th <pre>
message_labels = ('to', 'subject', 'from', 'date', 'message-id', 'content-type')
message_labels = ('to', 'subject', 'from', 'date', 'message-id', 'content-type')
# mhonarc xcomments
# ref: http://www.schlaubert.de/MHonArc/doc/resources/printxcomments.html
message['subject'] = parse_xcomment(soup, "X-Subject")
message['date'] = parse_xcomment(soup, "X-Date")
message['from'] = parse_xcomment(soup, "X-From-R13") #useless...
message['message-id'] = parse_xcomment(soup, 'X-Message-Id')
message['content-type'] = parse_xcomment(soup, 'X-Content-Type')
# mhonarc xcomments
# ref: http://www.schlaubert.de/MHonArc/doc/resources/printxcomments.html
message['subject'] = parse_xcomment(soup, "X-Subject")
message['date'] = parse_xcomment(soup, "X-Date")
message['from'] = parse_xcomment(soup, "X-From-R13") #useless...
message['message-id'] = parse_xcomment(soup, 'X-Message-Id')
message['content-type'] = parse_xcomment(soup, 'X-Content-Type')
# parse what is displayed on the page
# parse what is displayed on the page
info = soup.select('ul:nth-of-type(1) > li')
info = soup.select('ul:nth-of-type(1) > li')
for i in info:
if i.em == None:
continue
field = i.em.string
if field.lower() in message_labels:
message[field.lower()] = i.text.strip(field + ": ")
for i in info:
if i.em == None:
continue
field = i.em.string
if field.lower() in message_labels:
message[field.lower()] = i.text.strip(field + ": ")
## reformat from -- [author_name, email_addr]
## reformat from -- [author_name, email_addr]
# from_addr = email.utils.parseaddr(message['from'])
# message['author_name'] = from_addr[0]
# message['from'] = from_addr[1]
# from_addr = email.utils.parseaddr(message['from'])
# message['author_name'] = from_addr[0]
# message['from'] = from_addr[1]
## -- content --
# test
# c1 = soup.select('pre:nth-of-type(1)')
# if len(c1) > 0:
# message['content'] = c1[0].text
# else:
# message['content'] = soup.select('pre:nth-of-type(2)')[0].text
## -- content --
# test
# c1 = soup.select('pre:nth-of-type(1)')
# if len(c1) > 0:
# message['content'] = c1[0].text
# else:
# message['content'] = soup.select('pre:nth-of-type(2)')[0].text
message['content'] = soup.select('pre:nth-of-type(2)')[0].text
message['content'] = soup.select('pre:nth-of-type(2)')[0].text
# mhonarc xcomments
# ref: http://www.schlaubert.de/MHonArc/doc/resources/printxcomments.html
def parse_xcomment(soup, xcom):
com = soup.find(text=re.compile(xcom))
if com is not None:
return com.strip('<!-- ').strip(' -->').strip(xcom + ":").strip()
return com
com = soup.find(text=re.compile(xcom))
if com is not None:
return com.strip('<!-- ').strip(' -->').strip(xcom + ":").strip()
return com
def test_xcomment(soup):
return soup.find(text=re.compile('X-Message-Id')) is not None
return soup.find(text=re.compile('X-Message-Id')) is not None

79
www/archives.py
View File

@ -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

5
www/routes.py
View File

@ -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():

BIN
www/static/CYBERPLA.GIF Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 527 B

BIN
www/static/cover.gif Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 4.7 KiB

BIN
www/static/favicon.ico Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 894 B

17
www/static/ooo.js Normal file
View File

@ -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);
};

7
www/static/search.js
View File

@ -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>";

11
www/templates/index.html
View File

@ -1,6 +1,11 @@
<html>
<head></head>
<body>
<a href="/search"><h3>---> SEARCH <---</h3></a>
<head>
<title>Times of Nettime</title>
<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>

14
www/templates/search.html
View File

@ -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>