From 36b64d7e1be8fc6aed9ae8fa2ab6b6df0e3b43e9 Mon Sep 17 00:00:00 2001
From: mjanowiecki <32551917+mjanowiecki@users.noreply.github.com>
Date: Tue, 20 Nov 2018 12:14:56 -0500
Subject: [PATCH 1/3] added bib number to csv

---
 getTopContainerCountByResource.py | 60 ++++++++++++++++++-------------
 1 file changed, 36 insertions(+), 24 deletions(-)

diff --git a/getTopContainerCountByResource.py b/getTopContainerCountByResource.py
index 0cab6eb..c8455cc 100644
--- a/getTopContainerCountByResource.py
+++ b/getTopContainerCountByResource.py
@@ -19,7 +19,7 @@
 ids = requests.get(baseURL + endpoint, headers=headers).json()
 
 f=csv.writer(open('topContainerCountByResource.csv', 'wb'))
-f.writerow(['title']+['uri']+['id_0']+['id_1']+['id_2']+['id_3']+['topContainerCount'])
+f.writerow(['title']+['bib']+['uri']+['id_0']+['id_1']+['id_2']+['id_3']+['topContainerCount'])
 
 f2=csv.writer(open('topContainersLinks.csv', 'wb'))
 f2.writerow(['resourceUri']+['topContainerUri'])
@@ -32,14 +32,19 @@
 topContainerLinks = []
 uniqueTopContainers = []
 for id in ids:
-
     resourceTopContainers = []
     print 'id', id, total, 'records remaining'
     total = total - 1
     endpoint = '/repositories/3/resources/'+str(id)
     output = requests.get(baseURL + endpoint, headers=headers).json()
     title = output['title'].encode('utf-8')
+    print title
     uri = output['uri']
+    try:
+        bib = output['user_defined']['real_1']
+    except:
+        bib =''
+    print bib
     id0 = output['id_0']
     try:
         id1 = output['id_1']
@@ -52,23 +57,27 @@
     try:
         id3 = output['id_3']
     except:
-        id3=''
-    # ###searchEndpoint = '/repositories/3/top_containers/search'
-    # ###output = requests.get(baseURL + searchEndpoint, headers=headers).json()
+        id3= ''
     page = 1
-    payload = {'page': page, 'page_size': '3000', 'root_record': endpoint}
-    search = requests.get(baseURL+'/search', headers=headers, params=payload).json()
+    resultsPage = ''
+    # while resultsPage != []:
+    #     payload = {'page': page, 'offset': offset, 'page_size': '100', 'root_record': endpoint}
+    #     print payload
+    #     search = requests.get(baseURL+'/search', headers=headers, params=payload).json()
+    #     print search
+
+    # resultsPage = search['results']
+    # for result in resultsPage:
+    #     results.append(result)
     results = []
-    resultsPage = search['results']
-    for result in resultsPage:
-        results.append(result)
     while resultsPage != []:
-        page = page + 1
-        payload = {'page': page, 'page_size': '3000', 'root_record': endpoint}
+        print page
+        payload = {'page': page, 'page_size': '100', 'root_record': endpoint}
         search = requests.get(baseURL+'/search', headers=headers, params=payload).json()
         resultsPage = search['results']
         for result in resultsPage:
             results.append(result)
+        page = page + 1
 
     for result in results:
         try:
@@ -85,23 +94,26 @@
             topContainers = []
     topContainerCount = len(resourceTopContainers)
     print 'top containers', topContainerCount
-    f.writerow([title]+[uri]+[id0]+[id1]+[id2]+[id3]+[topContainerCount])
+    f.writerow([title]+[bib]+[uri]+[id0]+[id1]+[id2]+[id3]+[topContainerCount])
 
+print 'top container links'
 for topContainerLink in topContainerLinks:
     f2.writerow([topContainerLink[:topContainerLink.index('|')]]+[topContainerLink[topContainerLink.index('|')+1:]])
 
+print 'unique top containers'
 for topContainer in uniqueTopContainers:
-        search = requests.get(baseURL+topContainer, headers=headers).json()
-        try:
-            indicator = search['indicator']
-        except:
-            indicator = ''
-            
-        try:
-            barcode = search['barcode']
-        except:
-            barcode = ''
-        f3.writerow([topContainer]+[indicator]+[barcode])
+    print topContainer
+    search = requests.get(baseURL+topContainer, headers=headers).json()
+    try:
+        indicator = search['indicator']
+    except:
+        indicator = ''
+
+    try:
+        barcode = search['barcode']
+    except:
+        barcode = ''
+    f3.writerow([topContainer]+[indicator]+[barcode])
 
 elapsedTime = time.time() - startTime
 m, s = divmod(elapsedTime, 60)

From fc3d2b4f3b055fc8a4c6c0aa8479e19600cde210 Mon Sep 17 00:00:00 2001
From: mjanowiecki <32551917+mjanowiecki@users.noreply.github.com>
Date: Wed, 21 Nov 2018 09:55:44 -0500
Subject: [PATCH 2/3] changes

---
 .gitignore                        | 3 ++-
 getTopContainerCountByResource.py | 9 ---------
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/.gitignore b/.gitignore
index 6204478..02cb572 100644
--- a/.gitignore
+++ b/.gitignore
@@ -54,4 +54,5 @@ data/*
 *.json
 local/*
 *.xml
-*.xslx
\ No newline at end of file
+*.xslx
+FamilyAgentsFromCSV.py
diff --git a/getTopContainerCountByResource.py b/getTopContainerCountByResource.py
index c8455cc..44fbfb6 100644
--- a/getTopContainerCountByResource.py
+++ b/getTopContainerCountByResource.py
@@ -60,15 +60,6 @@
         id3= ''
     page = 1
     resultsPage = ''
-    # while resultsPage != []:
-    #     payload = {'page': page, 'offset': offset, 'page_size': '100', 'root_record': endpoint}
-    #     print payload
-    #     search = requests.get(baseURL+'/search', headers=headers, params=payload).json()
-    #     print search
-
-    # resultsPage = search['results']
-    # for result in resultsPage:
-    #     results.append(result)
     results = []
     while resultsPage != []:
         print page

From 6e55602317aaed569651ab289811ddfba647ba9e Mon Sep 17 00:00:00 2001
From: mjanowiecki <32551917+mjanowiecki@users.noreply.github.com>
Date: Wed, 21 Nov 2018 10:09:14 -0500
Subject: [PATCH 3/3] changesagain

---
 .gitignore | 1 -
 1 file changed, 1 deletion(-)

diff --git a/.gitignore b/.gitignore
index 02cb572..6c23154 100644
--- a/.gitignore
+++ b/.gitignore
@@ -55,4 +55,3 @@ data/*
 local/*
 *.xml
 *.xslx
-FamilyAgentsFromCSV.py