/
test_spider.py
194 lines (146 loc) · 4.18 KB
/
test_spider.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
from scrapy.crawler import CrawlerProcess
from tinydb import Query
import os
import json
import pytest
from multiprocessing import Process
from main_spider import MainSpider
from db import init_db
@pytest.mark.skip(reason='Helper function to remove db file')
def remove_path(path):
if os.path.exists(path):
os.remove(path)
@pytest.mark.skip(reason='Helper function to create a new process')
def create_process(url_items, db):
def crawl():
crawler = CrawlerProcess(settings={
'LOG_ENABLED': False,
'TELNETCONSOLE_ENABLED': False,
})
crawler.crawl(MainSpider, url_items=url_items, db=db)
crawler.start()
process = Process(target=crawl)
process.start()
process.join()
def test_normal():
db_path = 'test_normal.json'
remove_path(db_path)
db = init_db(db_path)
correct_output = {
'url': 'http://motherfuckingwebsite.com/',
'regex': 'light(weight)?',
'matches': [
{
'text': 'lightweight',
'start': 573,
'end': 584,
},
{
'text': 'lightweight',
'start': 1554,
'end': 1565,
},
],
}
url_items = [
{
'url': 'http://motherfuckingwebsite.com/',
'regex': 'light(weight)?',
}
]
create_process(url_items, db)
output_items = db.all()
assert(len(output_items) > 0)
item = output_items[0]
assert(len(correct_output['matches']) == len(item['matches']))
for i in range(len(item['matches'])):
for key in item['matches'][i].keys():
assert(correct_output['matches'][i][key] == item['matches'][i][key])
remove_path(db_path)
def test_pattern_not_found():
db_path = 'test_normal.json'
remove_path(db_path)
db = init_db(db_path)
url_items = [
{
'url': 'http://motherfuckingwebsite.com/',
'regex': 'Finland',
}
]
create_process(url_items, db)
output_items = db.all()
assert(len(output_items) > 0)
item = output_items[0]
assert(len(item['matches']) == 0)
remove_path(db_path)
def test_wrong_url():
db_path = 'test_404_page.json'
remove_path(db_path)
db = init_db(db_path)
url_items = [
{
'url': 'http://cuchidatluaanhhung.com/',
'regex': 'Finland',
}
]
create_process(url_items, db)
output_items = db.all()
assert(len(output_items) == 0)
remove_path(db_path)
def test_redirect_url():
db_path = 'test_redirect_url.json'
remove_path(db_path)
db = init_db(db_path)
url_items = [
{
'url': 'https://about.google.com/', # 301 HTTP code
'regex': 'Policy',
}
]
correct_output = {
'matches': [
{
'text': 'Policy',
'start': 24355,
'end': 24361,
}
],
}
create_process(url_items, db)
output_items = db.all()
assert(len(output_items) > 0)
item = output_items[0]
assert(len(correct_output['matches']) == len(item['matches']))
for i in range(len(item['matches'])):
for key in item['matches'][i].keys():
assert(correct_output['matches'][i][key] == item['matches'][i][key])
remove_path(db_path)
def test_shorten_url():
db_path = 'test_shorten_url.json'
remove_path(db_path)
db = init_db(db_path)
url_items = [
{
'url': 'https://shorturl.at/giAL4', # 301 HTTP code
'regex': 'dribbble',
}
]
correct_output = {
'matches': [
{
'text': 'dribbble',
'start': 2628,
'end': 2636,
},
],
}
create_process(url_items, db)
output_items = db.all()
assert(len(output_items) > 0)
item = output_items[0]
assert(len(correct_output['matches']) == len(item['matches']))
for i in range(len(item['matches'])):
for key in item['matches'][i].keys():
assert(correct_output['matches'][i][key] == item['matches'][i][key])
remove_path(db_path)
test_shorten_url()