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
|
"""
This module contains some assorted functions used in tests
"""
from __future__ import absolute_import
import os
from importlib import import_module
from twisted.trial.unittest import SkipTest
from scrapy.exceptions import NotConfigured
from scrapy.utils.boto import is_botocore
def assert_aws_environ():
"""Asserts the current environment is suitable for running AWS testsi.
Raises SkipTest with the reason if it's not.
"""
skip_if_no_boto()
if 'AWS_ACCESS_KEY_ID' not in os.environ:
raise SkipTest("AWS keys not found")
def assert_gcs_environ():
if 'GCS_PROJECT_ID' not in os.environ:
raise SkipTest("GCS_PROJECT_ID not found")
def skip_if_no_boto():
try:
is_botocore()
except NotConfigured as e:
raise SkipTest(e)
def get_s3_content_and_delete(bucket, path, with_key=False):
""" Get content from s3 key, and delete key afterwards.
"""
if is_botocore():
import botocore.session
session = botocore.session.get_session()
client = session.create_client('s3')
key = client.get_object(Bucket=bucket, Key=path)
content = key['Body'].read()
client.delete_object(Bucket=bucket, Key=path)
else:
import boto
# assuming boto=2.2.2
bucket = boto.connect_s3().get_bucket(bucket, validate=False)
key = bucket.get_key(path)
content = key.get_contents_as_string()
bucket.delete_key(path)
return (content, key) if with_key else content
def get_gcs_content_and_delete(bucket, path):
from google.cloud import storage
client = storage.Client(project=os.environ.get('GCS_PROJECT_ID'))
bucket = client.get_bucket(bucket)
blob = bucket.get_blob(path)
content = blob.download_as_string()
bucket.delete_blob(path)
return content, blob
def get_crawler(spidercls=None, settings_dict=None):
"""Return an unconfigured Crawler object. If settings_dict is given, it
will be used to populate the crawler settings with a project level
priority.
"""
from scrapy.crawler import CrawlerRunner
from scrapy.spiders import Spider
runner = CrawlerRunner(settings_dict)
return runner.create_crawler(spidercls or Spider)
def get_pythonpath():
"""Return a PYTHONPATH suitable to use in processes so that they find this
installation of Scrapy"""
scrapy_path = import_module('scrapy').__path__[0]
return os.path.dirname(scrapy_path) + os.pathsep + os.environ.get('PYTHONPATH', '')
def get_testenv():
"""Return a OS environment dict suitable to fork processes that need to import
this installation of Scrapy, instead of a system installed one.
"""
env = os.environ.copy()
env['PYTHONPATH'] = get_pythonpath()
return env
def assert_samelines(testcase, text1, text2, msg=None):
"""Asserts text1 and text2 have the same lines, ignoring differences in
line endings between platforms
"""
testcase.assertEqual(text1.splitlines(), text2.splitlines(), msg)
|
