old dump history, started reorg as package

dump_history.py

@@ -0,0 +1,38 @@
+#!/usr/bin/env python
+from __future__ import print_function
+from argparse import ArgumentParser
+import json, sys
+from urllib import urlencode
+from urllib2 import urlopen, HTTPError, URLError
+
+p = ArgumentParser("")
+p.add_argument("padid", help="the padid")
+p.add_argument("--startrev", type=int, default=2, help="starting revision")
+p.add_argument("--endrev", type=int, default=None, help="ending revision, default: last")
+p.add_argument("--padinfo", default="padinfo.json", help="padinfo, default: padinfo.json")
+p.add_argument("--dir", default="out")
+args = p.parse_args()
+
+with open(args.padinfo) as f:
+	info = json.load(f)
+apiurl =  "{0[protocol]}://{0[hostname]}:{0[port]}{0[apiurl]}{0[apiversion]}/".format(info)
+data = {}
+data['apikey'] = info['apikey']
+data['padID'] = args.padid.encode("utf-8")
+
+
+total_revisions = apiurl+'getRevisionsCount?'+urlencode(data)
+total_revisions = json.load(urlopen(total_revisions))['data']['revisions']
+rev = args.startrev 
+print ("Dumping {0} revisions...".format(total_revisions), file=sys.stderr)
+
+data['startRev'] = "1"
+while rev <= total_revisions:
+	data['endRev'] = "{0}".format(rev)
+	requesturl = apiurl+'createDiffHTML?'+urlencode(data)
+	html = json.load(urlopen(requesturl))['data']['html']
+	out = "{0}/{1}_{2:06d}.html".format(args.dir, args.padid, rev)
+	print ("writing {0}".format(out), file=sys.stderr)
+	with open(out, "w") as f:
+		f.write(html.encode("utf-8"))
+	rev += 1

padinfo.sample.json

@@ -1,8 +0,0 @@
-{
-	"protocol": "http",
-    "hostname": "localhost",
-    "port": 9001,
-    "apiurl": "/api/",
-    "apiversion": "1.2.9",
-    "apikey": "XXXXXXXXXXXXXXXXXXXXXXXXX"
-}

setup.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python
+import distutils.command.install_lib
+from distutils.core import setup
+import os
+
+def find (p, d):
+    ret = []
+    for b, dd, ff in os.walk(os.path.join(p, d)):
+
+        for f in ff:
+            if not f.startswith("."):
+                fp = os.path.join(b, f)
+                ret.append(os.path.relpath(fp, p))
+    ret.sort()
+    # for x in ret[:10]:
+    #     print "**", x
+    return ret
+
+setup(
+    name='etherdump',
+    version='0.3.0',
+    author='Michael Murtaugh',
+    author_email='mm@automatist.org',
+    packages=['etherdump'],
+    package_dir={'etherdump': 'etherdump'},
+    #package_data={'activearchives': find("activearchives", "templates/") + find("activearchives", "data/")},
+    package_data={'etherdump': find("etherdump", "data/")},
+    scripts=['bin/etherdump'],
+    url='http://activearchives.org/wiki/Etherdump/',
+    license='LICENSE.txt',
+    description='Etherdump an etherpad publishing & archiving system',
+    # long_description=open('README.md').read(),
+    install_requires=[
+         "html5lib", "jinja2"
+    ]
+)