add innovation scrAper
Former-commit-id: 80558a9217d1bcad0766200d0e1d42aa022ff501
--- a/couchdb/settee/src/classes/SetteeDatabase.class.php
+++ b/couchdb/settee/src/classes/SetteeDatabase.class.php
@@ -251,7 +251,7 @@
*
* @return void
*/
- function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false) {
+ function get_view($design_doc, $view_name, $key = null, $descending = false, $limit = false, $reduce=null) {
$id = "_design/" . urlencode($design_doc);
$view_name = urlencode($view_name);
$id .= "/_view/$view_name";
@@ -269,6 +269,13 @@
if ($descending) {
$data .= "&descending=true";
}
+ if ($reduce != null) {
+ if ($reduce == true) {
+ $data .= "&reduce=true";
+ } else {
+ $data .= "&reduce=false";
+ }
+ }
if ($limit) {
$data .= "&limit=".$limit;
}
@@ -281,9 +288,11 @@
}
$full_uri = $this->dbname . "/" . $this->safe_urlencode($id);
+
$full_uri = str_replace("%253Fgroup%253D","?group=",$full_uri);
$full_uri = str_replace("%253Flimit%253D","?limit=",$full_uri);
$ret = $this->rest_client->http_get($full_uri, $data);
+ //$ret['decoded'] = str_replace("?k","&k",$ret['decoded']);
return $ret['decoded'];
}
--- a/documents/about.php
+++ b/documents/about.php
@@ -1,7 +1,7 @@
<?php
include('template.inc.php');
-include_header_documents("");
+include_header_documents("About");
include_once('../include/common.inc.php');
?>
<h1>About</h1>
--- /dev/null
+++ b/documents/agency.php
@@ -1,1 +1,41 @@
+<?php
+include('template.inc.php');
+include_once('../include/common.inc.php');
+$agenciesdb = $server->get_db('disclosr-agencies');
+$idtoname = Array();
+foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) {
+ $idtoname[$row->id] = trim($row->value->name);
+}
+$foidocsdb = $server->get_db('disclosr-foidocuments');
+
+include_header_documents((isset($_REQUEST['id']) ? $idtoname[$_REQUEST['id']] : 'Entries by Agency'));
+$endkey = (isset($_REQUEST['end_key']) ? $_REQUEST['end_key'] : '9999-99-99');
+?>
+<div class="headline">Read all the information released by Australian Federal Government agencies under the FOI Act in one place!</div>
+<a style='float:right' href="rss.xml.php"><img src="img/feed-icon-14x14.png" alt="RSS Icon"/> All Agencies RSS Feed</a><br>
+<?php
+try {
+ if ($_REQUEST['id']) {
+ $rows = $foidocsdb->get_view("app", "byAgencyID", $_REQUEST['id'], false, false, false)->rows;
+ foreach ($rows as $row) {
+ //print_r($rows);
+ echo displayLogEntry($row, $idtoname);
+ if (!isset($startkey))
+ $startkey = $row->key;
+ $endkey = $row->key;
+ }
+ } else {
+ $rows = $foidocsdb->get_view("app", "byAgencyID?group=true", null, false, false, true)->rows;
+ if ($rows) {
+ foreach ($rows as $row) {
+ echo '<a href="agency.php?id=' . $row->key . '">' . $idtoname[$row->key] . " (" . $row->value . " records)</a> <br>\n";
+ }
+ }
+ }
+} catch (SetteeRestClientException $e) {
+ setteErrorHandler($e);
+}
+echo "<a class='btn btn-large btn-primary' href='?end_key=$endkey' style='float:right;'>next page <i class='icon-circle-arrow-right icon-white'></i></a>";
+include_footer_documents();
+?>
--- a/documents/charts.php
+++ b/documents/charts.php
@@ -1,6 +1,6 @@
<?php
include('template.inc.php');
-include_header_documents("");
+include_header_documents("Charts");
include_once('../include/common.inc.php');
$agenciesdb = $server->get_db('disclosr-agencies');
@@ -15,29 +15,28 @@
<h1><a href="about.php">Charts</a></h1>
<h4 class="subheader">Lorem ipsum.</h4>
</div>
-<div id="employees" style="width:1000px;height:900px;"></div>
+<div id="bydate" style="width:1000px;height:300px;"></div>
+<div id="byagency" style="width:1200px;height:300px;"></div>
<script id="source">
window.onload = function() {
$(document).ready(function() {
var
d1 = [],
- start = new Date("2009/01/01 01:00").getTime(),
- options,
- graph,
- i, x, o;
+ options1,
+ o1;
<?php
try {
- $rows = $foidocsdb->get_view("app", "byDate?group=true", null, true)->rows;
+ $rows = $foidocsdb->get_view("app", "byDateMonthYear?group=true",null, false,false,true)->rows;
$dataValues = Array();
foreach ($rows as $row) {
- $dataValues[$row->value] = $row->key;
+ $dataValues[$row->key] = $row->value;
}
$i = 0;
ksort($dataValues);
- foreach ($dataValues as $value => $key) {
+ foreach ($dataValues as $key => $value) {
$date = date_create_from_format('Y-m-d', $key);
if (date_format($date, 'U') != "") {
echo " d1.push([".date_format($date, 'U')."000, $value]);" . PHP_EOL;
@@ -52,7 +51,7 @@
- options = {
+ options1 = {
xaxis : {
mode : 'time',
labelsAngle : 45
@@ -68,19 +67,19 @@
function drawGraph (opts) {
// Clone the options, so the 'options' variable always keeps intact.
- o = Flotr._.extend(Flotr._.clone(options), opts || {});
+ o1 = Flotr._.extend(Flotr._.clone(options1), opts || {});
// Return a new graph.
return Flotr.draw(
- document.getElementById("employees"),
+ document.getElementById("bydate"),
[ d1 ],
- o
+ o1
);
}
graph = drawGraph();
- Flotr.EventAdapter.observe(container, 'flotr:select', function(area){
+ Flotr.EventAdapter.observe(document.getElementById("bydate"), 'flotr:select', function(area){
// Draw selected area
graph = drawGraph({
xaxis : { min : area.x1, max : area.x2, mode : 'time', labelsAngle : 45 },
@@ -89,10 +88,74 @@
});
// When graph is clicked, draw the graph with default area.
- Flotr.EventAdapter.observe(container, 'flotr:click', function () { graph = drawGraph(); });
+ Flotr.EventAdapter.observe(document.getElementById("bydate"), 'flotr:click', function () { graph = drawGraph(); });
});
};
+
+var d2 = [];
+var agencylabels = [];
+function agencytrackformatter(obj) {
+
+ return agencylabels[Math.floor(obj.x)] +" = "+obj.y;
+
+ }
+ function agencytickformatter(val, axis) {
+ if (agencylabels[Math.floor(val)]) {
+ return '<p style="margin-top:8em;-webkit-transform:rotate(-90deg);">'+(agencylabels[Math.floor(val)])+"</b>";
+
+ } else {
+ return "";
+ }
+ }
+<?php
+ try {
+ $rows = $foidocsdb->get_view("app", "byAgencyID?group=true",null, false,false,true)->rows;
+
+
+ $dataValues = Array();
+ $i = 0;
+ foreach ($rows as $row) {
+ echo " d2.push([".$i.", $row->value]);" . PHP_EOL;
+ echo " agencylabels.push(['".str_replace("'","",$idtoname[$row->key])."']);" . PHP_EOL;
+
+ $i++;
+ }
+ } catch (SetteeRestClientException $e) {
+ setteErrorHandler($e);
+ }
+ ?>
+ // Draw the graph
+ Flotr.draw(
+ document.getElementById("byagency"),
+ [d2],
+ {
+ bars : {
+ show : true,
+ horizontal : false,
+ shadowSize : 0,
+ barWidth : 0.5
+ },
+mouse : {
+ track : true,
+ relative : true,
+ trackFormatter: agencytrackformatter
+ },
+ yaxis : {
+ min : 0,
+ autoscaleMargin : 1
+ },
+ xaxis: {
+ minorTickFreq: 1,
+ noTicks: agencylabels.length,
+ showMinorLabels: true,
+ tickFormatter: agencytickformatter
+ },
+ legend: {
+ show: false
+ }
+ }
+ );
</script>
<?php
--- /dev/null
+++ b/documents/date.php
@@ -1,1 +1,34 @@
+<?php
+include('template.inc.php');
+include_header_documents("Entries by Date");
+include_once('../include/common.inc.php');
+$endkey = (isset($_REQUEST['end_key']) ? $_REQUEST['end_key'] : '9999-99-99');
+?>
+<div class="headline">Read all the information released by Australian Federal Government agencies under the FOI Act in one place!</div>
+<a style='float:right' href="rss.xml.php"><img src="img/feed-icon-14x14.png" alt="RSS Icon"/> All Agencies RSS Feed</a><br>
+<?php
+/*$agenciesdb = $server->get_db('disclosr-agencies');
+
+$idtoname = Array();
+foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) {
+ $idtoname[$row->id] = trim($row->value->name);
+}
+$foidocsdb = $server->get_db('disclosr-foidocuments');
+try {
+ $rows = $foidocsdb->get_view("app", "byDate", Array($endkey, '0000-00-00'), true, 20)->rows;
+ if ($rows) {
+ foreach ($rows as $key => $row) {
+ echo displayLogEntry($row, $idtoname);
+ if (!isset($startkey)) $startkey = $row->key;
+ $endkey = $row->key;
+ }
+ }
+} catch (SetteeRestClientException $e) {
+ setteErrorHandler($e);
+}
+echo "<a class='btn btn-large btn-primary' href='?end_key=$endkey' style='float:right;'>next page <i class='icon-circle-arrow-right icon-white'></i></a>";
+*/
+include_footer_documents();
+?>
+
--- a/documents/disclogsList.php
+++ b/documents/disclogsList.php
@@ -1,7 +1,7 @@
<?php
include('template.inc.php');
-include_header_documents("");
+include_header_documents("List of Disclosure Logs");
include_once('../include/common.inc.php');
echo "<table>
--- /dev/null
+++ b/documents/disclosr-documents.nja
@@ -1,1 +1,7 @@
-
+{
+ "venv": "",
+ "project-type": "Import from sources",
+ "name": "disclosr-documents",
+ "license": "GNU General Public License v3",
+ "description": ""
+}
--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -13,11 +13,9 @@
from datetime import *
import codecs
+import difflib
+
from StringIO import StringIO
-
-from docx import *
-from lxml import etree
-import zipfile
from pdfminer.pdfparser import PDFDocument, PDFParser
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter, process_pdf
@@ -39,20 +37,45 @@
""" disclosr agency id """
if self.agencyID is None:
self.agencyID = os.path.basename(sys.argv[0]).replace(".py", "")
- return self.agencyID
+ return self.agencyID
def getURL(self):
""" disclog URL"""
if self.disclogURL is None:
agency = scrape.agencydb.get(self.getAgencyID())
self.disclogURL = agency['FOIDocumentsURL']
- return self.disclogURL
+ return self.disclogURL
@abc.abstractmethod
def doScrape(self):
""" do the scraping """
return
+class GenericHTMLDisclogScraper(GenericDisclogScraper):
+
+ def doScrape(self):
+ foidocsdb = scrape.couch['disclosr-foidocuments']
+ (url, mime_type, rcontent) = scrape.fetchURL(scrape.docsdb,
+ self.getURL(), "foidocuments", self.getAgencyID())
+ content = rcontent.read()
+ dochash = scrape.mkhash(content)
+ doc = foidocsdb.get(dochash)
+ if doc is None:
+ print "saving " + dochash
+ description = "This log may have updated but as it was not in a table last time we viewed it, we cannot extract what has changed. Please refer to the agency's website Disclosure Log to see the most recent entries"
+ last_attach = scrape.getLastAttachment(scrape.docsdb, self.getURL())
+ if last_attach != None:
+ html_diff = difflib.HtmlDiff()
+ description = description + "\nChanges: "
+ description = description + html_diff.make_table(last_attach.read().split('\n'),
+ content.split('\n'))
+ edate = date.today().strftime("%Y-%m-%d")
+ doc = {'_id': dochash, 'agencyID': self.getAgencyID()
+ , 'url': self.getURL(), 'docID': dochash,
+ "date": edate, "title": "Disclosure Log Updated", "description": description}
+ foidocsdb.save(doc)
+ else:
+ print "already saved"
class GenericPDFDisclogScraper(GenericDisclogScraper):
@@ -62,14 +85,15 @@
self.getURL(), "foidocuments", self.getAgencyID())
laparams = LAParams()
rsrcmgr = PDFResourceManager(caching=True)
- outfp = StringIO.StringIO()
+ outfp = StringIO()
device = TextConverter(rsrcmgr, outfp, codec='utf-8',
laparams=laparams)
- fp = StringIO.StringIO()
- fp.write(content)
- description = output.getvalue()
+ fp = StringIO()
+ fp.write(content.read())
+
process_pdf(rsrcmgr, device, fp, set(), caching=True,
check_extractable=True)
+ description = outfp.getvalue()
fp.close()
device.close()
outfp.close()
@@ -77,11 +101,10 @@
doc = foidocsdb.get(dochash)
if doc is None:
print "saving " + dochash
- edate = datetime.fromtimestamp(mktime()).strftime("%Y-%m-%d")
+ edate = date.today().strftime("%Y-%m-%d")
doc = {'_id': dochash, 'agencyID': self.getAgencyID()
, 'url': self.getURL(), 'docID': dochash,
- "date": edate, "title": "Disclosure Log Updated"}
- self.getDescription(entry, entry, doc)
+ "date": edate, "title": "Disclosure Log Updated", "description": description}
foidocsdb.save(doc)
else:
print "already saved"
@@ -103,17 +126,16 @@
for paratext in paratextlist:
newparatextlist.append(paratext.encode("utf-8"))
## Print our documnts test with two newlines under each paragraph
- description = '\n\n'.join(newparatextlist)
+ description = '\n\n'.join(newparatextlist).strip(' \t\n\r')
dochash = scrape.mkhash(description)
doc = foidocsdb.get(dochash)
if doc is None:
print "saving " + dochash
- edate = datetime.fromtimestamp(mktime()).strftime("%Y-%m-%d")
+ edate = time().strftime("%Y-%m-%d")
doc = {'_id': dochash, 'agencyID': self.getAgencyID()
, 'url': self.getURL(), 'docID': dochash,
- "date": edate, "title": "Disclosure Log Updated"}
- self.getDescription(entry, entry, doc)
+ "date": edate, "title": "Disclosure Log Updated", "description": description}
foidocsdb.save(doc)
else:
print "already saved"
@@ -201,10 +223,9 @@
(url, mime_type, content) = scrape.fetchURL(scrape.docsdb,
self.getURL(), "foidocuments", self.getAgencyID())
if content is not None:
- if mime_type is "text/html"\
- or mime_type is "application/xhtml+xml"\
- or mime_type is"application/xml":
+ if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type == "application/xml":
# http://www.crummy.com/software/BeautifulSoup/documentation.html
+ print "parsing"
soup = BeautifulSoup(content)
table = self.getTable(soup)
for row in self.getRows(table):
@@ -222,11 +243,11 @@
dochash = scrape.mkhash(
self.remove_control_chars(
url + (''.join(id.stripped_strings))))
- doc = foidocsdb.get(hash)
+ doc = foidocsdb.get(dochash)
if doc is None:
- print "saving " + hash
- doc = {'_id': hash,
+ print "saving " + dochash
+ doc = {'_id': dochash,
'agencyID': self.getAgencyID(),
'url': self.getURL(),
'docID': (''.join(id.stripped_strings))}
Binary files /dev/null and b/documents/img/feed-icon-14x14.png differ
--- a/documents/index.php
+++ b/documents/index.php
@@ -3,10 +3,11 @@
include('template.inc.php');
include_header_documents("");
include_once('../include/common.inc.php');
-$startkey = (isset($_REQUEST['start_key']) ? $_REQUEST['start_key'] : '9999-99-99');
+$endkey = (isset($_REQUEST['end_key']) ? $_REQUEST['end_key'] : '9999-99-99');
?>
+<div class="headline">Read all the information released by Australian Federal Government agencies under the FOI Act in one place!</div>
+<a style='float:right' href="rss.xml.php"><img src="img/feed-icon-14x14.png" alt="RSS Icon"/> All Agencies RSS Feed</a><br>
<?php
-
$agenciesdb = $server->get_db('disclosr-agencies');
$idtoname = Array();
@@ -15,17 +16,18 @@
}
$foidocsdb = $server->get_db('disclosr-foidocuments');
try {
- $rows = $foidocsdb->get_view("app", "byDate", Array($startkey, '0000-00-00'), true, 20)->rows;
+ $rows = $foidocsdb->get_view("app", "byDate", Array($endkey, '0000-00-00'), true, 20)->rows;
if ($rows) {
foreach ($rows as $key => $row) {
echo displayLogEntry($row, $idtoname);
+ if (!isset($startkey)) $startkey = $row->key;
$endkey = $row->key;
}
}
} catch (SetteeRestClientException $e) {
setteErrorHandler($e);
}
-echo "<a href='?start_key=$endkey'>next page</a>";
+echo "<a class='btn btn-large btn-primary' href='?end_key=$endkey' style='float:right;'>next page <i class='icon-circle-arrow-right icon-white'></i></a>";
include_footer_documents();
?>
--- a/documents/rss.xml.php
+++ b/documents/rss.xml.php
@@ -8,21 +8,28 @@
//Creating an instance of FeedWriter class.
$TestFeed = new RSS2FeedWriter();
//Setting the channel elements
-//Use wrapper functions for common channelelements
-$TestFeed->setTitle('disclosurelo.gs Newest Entries - All');
-$TestFeed->setLink('http://disclosurelo.gs/rss.xml.php');
-$TestFeed->setDescription('disclosurelo.gs Newest Entries - All Agencies');
-$TestFeed->setChannelElement('language', 'en-us');
-$TestFeed->setChannelElement('pubDate', date(DATE_RSS, time()));
-
-//Retriving informations from database
+////Retriving informations from database
$idtoname = Array();
$agenciesdb = $server->get_db('disclosr-agencies');
foreach ($agenciesdb->get_view("app", "byCanonicalName")->rows as $row) {
$idtoname[$row->id] = trim($row->value->name);
}
$foidocsdb = $server->get_db('disclosr-foidocuments');
-$rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99', '0000-00-00', 50), true)->rows;
+if (isset($_REQUEST['id'])) {
+ $rows = $foidocsdb->get_view("app", "byAgencyID", $_REQUEST['id'], false, false, false)->rows;
+ $title = $idtoname[$_REQUEST['id']];
+} else {
+ $rows = $foidocsdb->get_view("app", "byDate", Array('9999-99-99', '0000-00-00', 50), true)->rows;
+ $title = 'All Agencies';
+}
+//Use wrapper functions for common channelelements
+$TestFeed->setTitle('disclosurelo.gs Newest Entries - '.$title);
+$TestFeed->setLink('http://disclosurelo.gs/rss.xml.php'.(isset($_REQUEST['id'])? '?id='.$_REQUEST['id'] : ''));
+$TestFeed->setDescription('disclosurelo.gs Newest Entries - '.$title);
+$TestFeed->setChannelElement('language', 'en-us');
+$TestFeed->setChannelElement('pubDate', date(DATE_RSS, time()));
+
+
//print_r($rows);
foreach ($rows as $row) {
//Create an empty FeedItem
--- a/documents/scrape.py
+++ b/documents/scrape.py
@@ -8,186 +8,198 @@
import time
import os
import mimetypes
-import re
import urllib
import urlparse
def mkhash(input):
- return hashlib.md5(input).hexdigest().encode("utf-8")
+ return hashlib.md5(input).hexdigest().encode("utf-8")
def canonurl(url):
- r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or ''
- if the URL looks invalid.
- >>> canonurl('\xe2\x9e\xa1.ws') # tinyarro.ws
- 'http://xn--hgi.ws/'
- """
- # strip spaces at the ends and ensure it's prefixed with 'scheme://'
- url = url.strip()
- if not url:
- return ''
- if not urlparse.urlsplit(url).scheme:
- url = 'http://' + url
-
- # turn it into Unicode
- #try:
- # url = unicode(url, 'utf-8')
- #except UnicodeDecodeError:
- # return '' # bad UTF-8 chars in URL
-
- # parse the URL into its components
- parsed = urlparse.urlsplit(url)
- scheme, netloc, path, query, fragment = parsed
-
- # ensure scheme is a letter followed by letters, digits, and '+-.' chars
- if not re.match(r'[a-z][-+.a-z0-9]*$', scheme, flags=re.I):
- return ''
- scheme = str(scheme)
-
- # ensure domain and port are valid, eg: sub.domain.<1-to-6-TLD-chars>[:port]
- match = re.match(r'(.+\.[a-z0-9]{1,6})(:\d{1,5})?$', netloc, flags=re.I)
- if not match:
- return ''
- domain, port = match.groups()
- netloc = domain + (port if port else '')
- netloc = netloc.encode('idna')
-
- # ensure path is valid and convert Unicode chars to %-encoded
- if not path:
- path = '/' # eg: 'http://google.com' -> 'http://google.com/'
- path = urllib.quote(urllib.unquote(path.encode('utf-8')), safe='/;')
-
- # ensure query is valid
- query = urllib.quote(urllib.unquote(query.encode('utf-8')), safe='=&?/')
-
- # ensure fragment is valid
- fragment = urllib.quote(urllib.unquote(fragment.encode('utf-8')))
-
- # piece it all back together, truncating it to a maximum of 4KB
- url = urlparse.urlunsplit((scheme, netloc, path, query, fragment))
- return url[:4096]
+ r"""Return the canonical, ASCII-encoded form of a UTF-8 encoded URL, or ''
+ if the URL looks invalid.
+ >>> canonurl('\xe2\x9e\xa1.ws') # tinyarro.ws
+ 'http://xn--hgi.ws/'
+ """
+ # strip spaces at the ends and ensure it's prefixed with 'scheme://'
+ url = url.strip()
+ if not url:
+ return ''
+ if not urlparse.urlsplit(url).scheme:
+ url = 'http://' + url
+
+ # turn it into Unicode
+ #try:
+ # url = unicode(url, 'utf-8')
+ #except UnicodeDecodeError:
+ # return '' # bad UTF-8 chars in URL
+
+ # parse the URL into its components
+ parsed = urlparse.urlsplit(url)
+ scheme, netloc, path, query, fragment = parsed
+
+ # ensure scheme is a letter followed by letters, digits, and '+-.' chars
+ if not re.match(r'[a-z][-+.a-z0-9]*$', scheme, flags=re.I):
+ return ''
+ scheme = str(scheme)
+
+ # ensure domain and port are valid, eg: sub.domain.<1-to-6-TLD-chars>[:port]
+ match = re.match(r'(.+\.[a-z0-9]{1,6})(:\d{1,5})?$', netloc, flags=re.I)
+ if not match:
+ return ''
+ domain, port = match.groups()
+ netloc = domain + (port if port else '')
+ netloc = netloc.encode('idna')
+
+ # ensure path is valid and convert Unicode chars to %-encoded
+ if not path:
+ path = '/' # eg: 'http://google.com' -> 'http://google.com/'
+ path = urllib.quote(urllib.unquote(path.encode('utf-8')), safe='/;')
+
+ # ensure query is valid
+ query = urllib.quote(urllib.unquote(query.encode('utf-8')), safe='=&?/')
+
+ # ensure fragment is valid
+ fragment = urllib.quote(urllib.unquote(fragment.encode('utf-8')))
+
+ # piece it all back together, truncating it to a maximum of 4KB
+ url = urlparse.urlunsplit((scheme, netloc, path, query, fragment))
+ return url[:4096]
def fullurl(url,href):
- href = href.replace(" ","%20")
- href = re.sub('#.*$','',href)
- return urljoin(url,href)
+ href = href.replace(" ","%20")
+ href = re.sub('#.*$','',href)
+ return urljoin(url,href)
#http://diveintopython.org/http_web_services/etags.html
-class NotModifiedHandler(urllib2.BaseHandler):
- def http_error_304(self, req, fp, code, message, headers):
- addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url())
- addinfourl.code = code
- return addinfourl
+class NotModifiedHandler(urllib2.BaseHandler):
+ def http_error_304(self, req, fp, code, message, headers):
+ addinfourl = urllib2.addinfourl(fp, headers, req.get_full_url())
+ addinfourl.code = code
+ return addinfourl
+
+def getLastAttachment(docsdb,url):
+ hash = mkhash(url)
+ doc = docsdb.get(hash)
+ if doc != None:
+ last_attachment_fname = doc["_attachments"].keys()[-1]
+ last_attachment = docsdb.get_attachment(doc,last_attachment_fname)
+ return last_attachment
+ else:
+ return None
def fetchURL(docsdb, url, fieldName, agencyID, scrape_again=True):
- url = canonurl(url)
- hash = mkhash(url)
- req = urllib2.Request(url)
- print "Fetching %s (%s)" % (url,hash)
- if url.startswith("mailto") or url.startswith("javascript") or url.startswith("#") or url == None or url == "":
- print "Not a valid HTTP url"
- return (None,None,None)
- doc = docsdb.get(hash)
- if doc == None:
- doc = {'_id': hash, 'agencyID': agencyID, 'url': url, 'fieldName':fieldName}
- else:
- if (('page_scraped' in doc) and (time.time() - doc['page_scraped']) < 60*24*14*1000):
- print "Uh oh, trying to scrape URL again too soon!"
- last_attachment_fname = doc["_attachments"].keys()[-1]
- last_attachment = docsdb.get_attachment(doc,last_attachment_fname)
- content = last_attachment
- return (doc['url'],doc['mime_type'],content)
- if scrape_again == False:
- print "Not scraping this URL again as requested"
- return (None,None,None)
-
- time.sleep(3) # wait 3 seconds to give webserver time to recover
-
- req.add_header("User-Agent", "Mozilla/4.0 (compatible; Prometheus webspider; owner maxious@lambdacomplex.org)")
- #if there is a previous version stored in couchdb, load caching helper tags
- if doc.has_key('etag'):
- req.add_header("If-None-Match", doc['etag'])
- if doc.has_key('last_modified'):
- req.add_header("If-Modified-Since", doc['last_modified'])
-
- opener = urllib2.build_opener(NotModifiedHandler())
- try:
- url_handle = opener.open(req)
- doc['url'] = url_handle.geturl() # may have followed a redirect to a new url
- headers = url_handle.info() # the addinfourls have the .info() too
- doc['etag'] = headers.getheader("ETag")
- doc['last_modified'] = headers.getheader("Last-Modified")
- doc['date'] = headers.getheader("Date")
- doc['page_scraped'] = time.time()
- doc['web_server'] = headers.getheader("Server")
- doc['via'] = headers.getheader("Via")
- doc['powered_by'] = headers.getheader("X-Powered-By")
- doc['file_size'] = headers.getheader("Content-Length")
- content_type = headers.getheader("Content-Type")
- if content_type != None:
- doc['mime_type'] = content_type.split(";")[0]
- else:
- (type,encoding) = mimetypes.guess_type(url)
- doc['mime_type'] = type
- if hasattr(url_handle, 'code'):
- if url_handle.code == 304:
- print "the web page has not been modified"
- return (None,None,None)
- else:
- content = url_handle.read()
- docsdb.save(doc)
- doc = docsdb.get(hash) # need to get a _rev
- docsdb.put_attachment(doc, content, str(time.time())+"-"+os.path.basename(url), doc['mime_type'])
- return (doc['url'], doc['mime_type'], content)
- #store as attachment epoch-filename
-
- except urllib2.URLError as e:
- error = ""
- if hasattr(e, 'reason'):
- error = "error %s in downloading %s" % (str(e.reason), url)
- elif hasattr(e, 'code'):
- error = "error %s in downloading %s" % (e.code, url)
- print error
- doc['error'] = error
- docsdb.save(doc)
- return (None,None,None)
+ url = canonurl(url)
+ hash = mkhash(url)
+ req = urllib2.Request(url)
+ print "Fetching %s (%s)" % (url,hash)
+ if url.startswith("mailto") or url.startswith("javascript") or url.startswith("#") or url == None or url == "":
+ print "Not a valid HTTP url"
+ return (None,None,None)
+ doc = docsdb.get(hash)
+ if doc == None:
+ doc = {'_id': hash, 'agencyID': agencyID, 'url': url, 'fieldName':fieldName}
+ else:
+ if (('page_scraped' in doc) and (time.time() - doc['page_scraped']) < 60*24*14*1000):
+ print "Uh 