From: Alex Sadleir Date: Sun, 03 Nov 2013 06:14:20 +0000 Subject: add example of mass delete in couchdb X-Git-Url: https://maxious.lambdacomplex.org/git/?p=disclosr.git&a=commitdiff&h=b332fbb1e648ab6f38eb160a430ff6f8f23d895b --- add example of mass delete in couchdb Former-commit-id: e4bf5639b70ec8e6053e0b10b7e2f275eb629b6a --- --- /dev/null +++ b/admin/massdelete.sh @@ -1,1 +1,10 @@ +for line in `curl "http://localhost:5984/disclosr-foidocuments/_design/app/_view/byAgencyID?reduce=false&keys=%5B\"5716ce0aacfe98f7d638b7a66b7f1040\"%5D&limit=600" | xargs -L1`; do +# echo $line + id=`echo $line | grep -Po '_id:.*?[^\\\],' | perl -pe 's/_id://; s/^//; s/,$//'` + rev=`echo $line | grep -Po 'rev:.*?[^\\\],'| perl -pe 's/rev://; s/^//; s/,$//'` + if [ -n "$id" ]; then + echo "curl -X DELETE http://localhost:5984/disclosr-foidocuments/$id?rev=$rev" + curl -X DELETE http://localhost:5984/disclosr-foidocuments/$id?rev=$rev + fi +done; --- a/documents/about.php +++ b/documents/about.php @@ -5,6 +5,7 @@ include_once('../include/common.inc.php'); ?>

About

+Written and managed by Alex Sadleir (maxious [at] lambdacomplex.org) --- a/documents/genericScrapers.py +++ b/documents/genericScrapers.py @@ -199,6 +199,17 @@ def getRows(self, table): return table.find_all('tr') + def getDocHash(self, id,date, url): + if id.string is None: + print "no id, using date as hash" + return scrape.mkhash( + self.remove_control_chars( + url + (''.join(date.stripped_strings)))) + else: + return scrape.mkhash( + self.remove_control_chars( + url + (''.join(id.stripped_strings)))) + def getDate(self, content, entry, doc): strdate = ''.join(content.stripped_strings).strip() (a, b, c) = strdate.partition("(") @@ -240,15 +251,7 @@ description, notes) = self.getColumns(columns) print self.remove_control_chars( ''.join(id.stripped_strings)) - if id.string is None: - print "no id, using date as hash" - dochash = scrape.mkhash( - self.remove_control_chars( - url + (''.join(date.stripped_strings)))) - else: - dochash = scrape.mkhash( - self.remove_control_chars( - url + (''.join(id.stripped_strings)))) + dochash = self.getDocHash(id,date,url) doc = foidocsdb.get(dochash) if doc is None: --- a/documents/runScrapers.sh +++ b/documents/runScrapers.sh @@ -1,3 +1,4 @@ +#!/bin/bash DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )" echo $DIR cd $DIR --- a/documents/scrapers/5716ce0aacfe98f7d638b7a66b7f1040.py +++ b/documents/scrapers/5716ce0aacfe98f7d638b7a66b7f1040.py @@ -6,6 +6,11 @@ #http://www.doughellmann.com/PyMOTW/abc/ class ScraperImplementation(genericScrapers.GenericOAICDisclogScraper): + def getDocHash(self, id,date, url): + ''' url changes on ever request so ignore for hash ''' + return scrape.mkhash( + self.remove_control_chars( + ''.join(id.stripped_strings))) def getColumnCount(self): return 4 def getColumns(self,columns): --- a/graph.php +++ b/graph.php @@ -9,13 +9,13 @@ function add_node($id, $label, $parent="") { global $format; if ($format == "html") { - // echo "nodes[\"$id\"] = graph.newNode({label: \"$label\"});" . PHP_EOL; + // echo "nodes[\"$id\"] = graph.newNode({label: \"$label\"});" . PHP_EOL; } if ($format == "dot" && $label != "") { - echo "$id [label=\"$label\"];". PHP_EOL; + echo "\"$id\" [label=\"$label\", shape=plaintext];". PHP_EOL; } if ($format == "gexf") { - echo "":">") + echo "":">") ."" ."". PHP_EOL; } @@ -27,7 +27,7 @@ // echo "graph.newEdge(nodes[\"$from\"], nodes['$to'], {color: '$color'});" . PHP_EOL; } if ($format == "dot") { - echo "$from -> $to ".($color != ""? "[color=$color]":"").";". PHP_EOL; + echo "\"$from\" -> \"$to\" ".($color != ""? "[color=$color]":"").";". PHP_EOL; } if ($format == "gexf") { echo "". PHP_EOL; @@ -55,7 +55,7 @@ $rows = $db->get_view("app", "byCanonicalName", null, true)->rows; //print_r($rows); foreach ($rows as $row) { - add_node($row->id, $row->key); + add_node($row->id, $row->value->name); } } catch (SetteeRestClientException $e) { setteErrorHandler($e); --- a/ranking.php +++ b/ranking.php @@ -32,8 +32,12 @@ $columnKeys = array_unique(array_merge($columnKeys, array_keys($columns))); //print_r($columnKeys); $score = count($columns); - $scores[$score]++; - $scoredagencies[] = Array("id"=> $row->key, "website"=> $row->value->website, "name" => $row->value->name, "columns" => $columns, "score" => $score); + if (isset($scores[$score])){ +$scores[$score]++; +} else { +$scores[$score] =1; +} + $scoredagencies[] = Array("id"=> $row->key, "website"=> (isset($row->value->website)?$row->value->website:""), "name" => $row->value->name, "columns" => $columns, "score" => $score); } } @@ -74,7 +78,7 @@ } else { $href = $value; } - if ($href[0] == "@") { + if (isset($href[0]) && $href[0] == "@") { $href = str_replace("@","https://twitter.com/",$href); } //$href= urlencode($href);