error reporting features
error reporting features


Former-commit-id: 4458096bdd46a0e420126ab910fbf68cbdd986f0

--- a/documents/genericScrapers.py
+++ b/documents/genericScrapers.py
@@ -72,7 +72,8 @@
             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":  self.remove_control_chars(description), "diff": diff}
+            "date": edate, "title": "Disclosure Log Updated", 
+	    "description":  self.remove_control_chars(description), "diff": self.remove_control_chars(diff)}
             foidocsdb.save(doc)
         else:
             print "already saved"
@@ -277,6 +278,6 @@
                         print "header row"
 
                     else:
-                        print "ERROR number of columns incorrect"
+                        print >> sys.stderr, "ERROR number of columns incorrect"
                         print row
 

--- a/documents/runScrapers.sh
+++ b/documents/runScrapers.sh
@@ -1,10 +1,20 @@
-for f in scrapers/*.py; 
-	do echo "Processing $f file.."; 
-	python $f; 
+echo "" > /tmp/disclosr-error
+for f in scrapers/*.py; do
+	echo "Processing $f file..";
+	md5=`md5sum /tmp/disclosr-error`
+	python $f 3>&1 1>&2 2>&3 | tee --append /tmp/disclosr-error;
+	md52=`md5sum /tmp/disclosr-error`
+	if [ "$md5" != "$md52" ]; then
+		echo "^^^^^^^^^^^^^^ $f" >> /tmp/disclosr-error;
+	fi
 	if [ "$?" -ne "0" ]; then
 		echo "error";
-		sleep 2; 
+		sleep 1;
 	fi
 done
+if [ -s /tmp/disclosr-error ] ; then
+    echo "emailling logs..";
+    mail -E -s "Disclosr errors" maxious@lambdacomplex.org < /tmp/disclosr-error ;
+fi
 
 

--- a/documents/scrape.py
+++ b/documents/scrape.py
@@ -7,14 +7,15 @@
 from urlparse import urljoin
 import time
 import os
+import sys
 import mimetypes
 import urllib
 import urlparse
 import socket
 
 #couch = couchdb.Server('http://192.168.1.148:5984/')
-couch = couchdb.Server('http://192.168.1.113:5984/')
-#couch = couchdb.Server('http://127.0.0.1:5984/')
+#couch = couchdb.Server('http://192.168.1.113:5984/')
+couch = couchdb.Server('http://127.0.0.1:5984/')
 
 
 def mkhash(input):
@@ -103,7 +104,7 @@
     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"
+        print >> sys.stderr, "Not a valid HTTP url"
         return (None, None, None)
     doc = docsdb.get(hash)
     if doc == None:
@@ -159,13 +160,13 @@
                 #store as attachment epoch-filename
 
     except (urllib2.URLError, socket.timeout) as e:
-        print "error!"
+        print >> sys.stderr,"error!"
         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
+        print >> sys.stderr, error
         doc['error'] = error
         docsdb.save(doc)
         return (None, None, None)

--- a/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py
+++ b/documents/scrapers/227cb6eb7d2c9f8a6e846df7447d6caa.py
@@ -18,13 +18,13 @@
                                         if mime_type == "text/html" or mime_type == "application/xhtml+xml" or mime_type =="application/xml":
                                         # http://www.crummy.com/software/BeautifulSoup/documentation.html
                                                 soup = BeautifulSoup(htcontent)
-                                                for row in soup.find(class_ = "ms-rteTable-GreyAlternating").find_all('tr'):
+						rowtitle = soup.find(class_ = "wc-title").find("h1").string
+                                                if rowtitle != None:
+                                                   description = rowtitle + ": "
+                                                for row in soup.find(class_ ="wc-content").find_all('td'):
                                                         if row != None:
-								rowtitle = row.find('th').string
-                                                                if rowtitle != None:
-                                                                    description = description + "\n" + rowtitle + ": "
-                                                                for text in row.find('td').stripped_strings:
-                                                                    description = description + text
+                                                                for text in row.stripped_strings:
+                                                                    description = description + text + "\n"
                                                      		for atag in row.find_all("a"):
                                                                 	if atag.has_key('href'):
                                                                         	links.append(scrape.fullurl(link,atag['href']))
@@ -37,7 +37,7 @@
 	def getColumnCount(self):
 		return 2
 	def getTable(self,soup):
-		return soup.find(class_ = "ms-rteTable-GreyAlternating")
+		return soup.find(class_ = "ms-rteTable-default")
 	def getColumns(self,columns):
 		(date, title) = columns
 		return (title, date, title, title, None)

--- a/documents/scrapers/f2ab2908d8ee56ed8d995ef4187e75e6.py
+++ b/documents/scrapers/f2ab2908d8ee56ed8d995ef4187e75e6.py
@@ -10,7 +10,7 @@
                 (id, date, title, description, notes) = columns
                 return (id, date, title, description, notes)
         def getTable(self,soup):
-                return soup.find(id = "content").table
+                return soup.find("table")
 
 if __name__ == '__main__':
     print 'Subclass:', issubclass(ScraperImplementation, genericScrapers.GenericOAICDisclogScraper)