Commit 0133bb31 authored by Andreas's avatar Andreas

sample for html fragment checksumming and creating of a watchlist

parent 8207c2d1
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"import json"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Create a WebarchivSession Object with convenience methods for easy access with your API-Key "
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"from webarchiv import WebarchivSession\n",
"\n",
"apikey = '2pm8i0hnmpcTK4Oj4CUeBoZd7vywrm4c'\n",
"w = WebarchivSession(apikey)\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"url = \"http://sport.orf.at/l/stories/2003717/\"\n",
"response = w.wayback_search(\"http://sport.orf.at/l/stories/2003717/\", \"20110101000000\", \"20120401000000\")\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"if response.status_code != 200:\n",
" print(\"Error \", response.status_code)\n"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"http://wayback/web/20110401202828/http://sport.orf.at/l/stories/2003717/\n",
"http://wayback/web/20110704202825/http://sport.orf.at/l/stories/2003717/\n",
"A watchlist with all captures mentioned above was generated. The code for this watchlist is Zp. \n",
"end\n"
]
}
],
"source": [
"lastchecksum = ''\n",
"captures = []\n",
"for capture in response.json()['hits']:\n",
" capturedate = capture['c']\n",
"\n",
" resp = w.fragment_checksum_html(url, capturedate, \".odd td\", 3)\n",
" checksum = resp.json()['checksum']\n",
" returncode = resp.json()['returncode']\n",
"\n",
" if returncode != 0:\n",
" continue\n",
"\n",
" if checksum != lastchecksum:\n",
" #print(resp.json())\n",
" print(\"http://wayback/web/\" + capturedate + \"/\" + url)\n",
" capture = {\"url\": url, \"timestamp\": capturedate}\n",
" captures.append(capture)\n",
" #print(capturedate + \" \" + checksum)\n",
"\n",
" lastchecksum = checksum\n",
"\n",
"if len(captures) > 0:\n",
" response = w.create_watchlist(captures)\n",
" print (\"A watchlist with all captures mentioned above was generated. The code for this watchlist is \" + response.json() + \". \" )\n",
" \n",
" \n",
"print(\"end\")\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.6.6"
}
},
"nbformat": 4,
"nbformat_minor": 1
}
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment