From 40b8b8c6bb549ede5379d4d5e198fcb39f6250de Mon Sep 17 00:00:00 2001
From: Saurabh Minni <saurabh@adnear.com>
Date: Fri, 17 Jun 2016 19:57:33 +0530
Subject: [PATCH] First commit of the code which does the basic work

---
 README.md            | 15 ++++++++++-
 slack_json_to_csv.py | 60 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+), 1 deletion(-)
 create mode 100644 slack_json_to_csv.py

diff --git a/README.md b/README.md
index 75e3423..78e4db2 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,15 @@
 # Slack-Export-JSON-to-CSV
-Convert Slack messages exported in their complicated JSON format to simple CSV format
+Convert Slack messages exported in their complicated JSON format to simple CSV formatpa
+
+To run the application use the following command
+
+```shell
+python slack_json_to_csv.py folder_of_channel_to_export path_to_slack_users.json path_to_output_slack_messages.csv
+
+```
+
+eg.
+
+```shell
+python slack_json_to_csv.py slack_export/channelA slack_export/users.json output.csv
+```
diff --git a/slack_json_to_csv.py b/slack_json_to_csv.py
new file mode 100644
index 0000000..7226f63
--- /dev/null
+++ b/slack_json_to_csv.py
@@ -0,0 +1,60 @@
+import json, sys
+import os, csv
+from pprint import pprint
+import re
+from datetime import datetime
+
+
+def handle_annotated_mention(matchobj):
+    return "@{}".format((matchobj.group(0)[2:-1]).split("|")[1])
+
+def handle_mention(matchobj):
+    global user
+    print(user[matchobj.group(0)[2:-1]][0])
+    return "@{}".format(user[matchobj.group(0)[2:-1]][0])
+
+
+def transform_text(text):
+    text = text.replace("<!channel>", "@channel")
+    text = text.replace("&gt;",  ">")
+    text = text.replace("&amp;", "&")
+    # Handle "<@U0BM1CGQY|the100rabh> has joined the channel"
+    text = re.compile("<@U\w+\|[A-Za-z0-9.-_]+>").sub(handle_annotated_mention, text)
+    text = re.compile("<@U\w+>").sub(handle_mention, text)
+    return text
+
+jsondir = sys.argv[1]
+userjson = sys.argv[2]
+outcsv_file = sys.argv[3]
+
+content_list = []
+userlist  = []
+f = open(outcsv_file, 'w')
+user = {};
+with open(userjson) as user_data:
+    userlist = json.load(user_data)
+    for userdata in userlist:
+        userid = userdata["id"]
+        if "real_name" in userdata and userdata["real_name"]:
+            realname = userdata["real_name"]
+            if not re.match('.*[a-zA-Z].*', realname) :
+                realname = userdata["name"]
+        else:
+            realname = userdata["name"]
+        print(realname)
+        user[userid] = [realname]
+csvwriter = csv.writer(f, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
+for content in os.listdir(jsondir):
+    content_list.append(content)
+    with open(jsondir + '/' + content) as data_file:
+        data = json.load(data_file)
+        for item in data:
+            if item["type"] == "message" :
+                if item["text"].find("> has joined the channel") == -1:
+                    user_cur = user[item["user"]]
+                    ts = datetime.utcfromtimestamp(float(item['ts']))
+                    time = ts.strftime("%Y-%m-%d %H:%M:%S")
+                    item["text"] = transform_text(item["text"])
+                    csvwriter.writerow([time.encode('utf-8'),item['text'].encode('utf-8'),user_cur[0].encode('utf-8')])
+
+f.close()