Newer
Older
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from webarchiv import WebarchivSession\n",
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
"w = WebarchivSession(apikey)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Submit a fulltext search to get a list of tophits per domain ordered by the largest number of hits"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"response = w.fulltext_search(\"Nationalbibliothek Prunksaal Schwarzenegger\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"The search always returns the full response. Checking for status_code 200 before extracting the response is always a good idea"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"if response.status_code != 200:\n",
" print(\"Something went wrong ...\")\n",
" exit(1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Now it is safe to extract the response"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Get the tophit of the domain with the largest number of hits which contains the words Nationalbliothek, Prunksaal and Schwarzenegger"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"http://www.onb.ac.at/services/21696.htm\n"
]
}
],
"source": [
"print (response.json()['hits'][0]['value'])\n"
]
}
],
"metadata": {
"kernelspec": {
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",