arachnid2 0.3.7 → 0.3.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/Gemfile.lock +14 -15
- data/lib/arachnid2/version.rb +1 -1
- data/lib/arachnid2/watir.rb +4 -5
- metadata +1 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: fb4b9682882053c38b4169d9b5644cec08e431afa1ae3c22323abe8091124b92
|
4
|
+
data.tar.gz: 79a08fec495dc55a95d41b65dad4c59cb08061ef13adc8d18bbcc374d46eb3f1
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e60c38afd2429656b477b017edf661124b4f40c8598dbeed106d8eec94bc77fbd2cd5f974133bd0118ee447b736869c837b20ce396a22e2ebd0661163ec9a493
|
7
|
+
data.tar.gz: 6cd1317b0de54db95772f6e30daafb95484fda231a4ef93c9b2e16a0fe6de8e2728aec9a293d81b6d95c5da8ce84b2c51184f2bf74d268c16c1c9cbe5999e421
|
data/Gemfile.lock
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
PATH
|
2
2
|
remote: .
|
3
3
|
specs:
|
4
|
-
arachnid2 (0.3.
|
4
|
+
arachnid2 (0.3.8)
|
5
5
|
addressable
|
6
6
|
adomain
|
7
7
|
bloomfilter-rb
|
@@ -21,23 +21,22 @@ GEM
|
|
21
21
|
logger
|
22
22
|
bloomfilter-rb (2.1.1)
|
23
23
|
redis
|
24
|
-
childprocess (
|
25
|
-
rake (< 13.0)
|
24
|
+
childprocess (3.0.0)
|
26
25
|
diff-lcs (1.3)
|
27
26
|
ethon (0.12.0)
|
28
27
|
ffi (>= 1.3.0)
|
29
28
|
facets (3.1.0)
|
30
|
-
ffi (1.
|
31
|
-
json (2.
|
32
|
-
logger (1.4.
|
29
|
+
ffi (1.12.2)
|
30
|
+
json (2.3.0)
|
31
|
+
logger (1.4.2)
|
33
32
|
mini_portile2 (2.4.0)
|
34
|
-
nokogiri (1.10.
|
33
|
+
nokogiri (1.10.8)
|
35
34
|
mini_portile2 (~> 2.4.0)
|
36
35
|
os (1.0.1)
|
37
36
|
psych (3.1.0)
|
38
|
-
public_suffix (4.0.
|
37
|
+
public_suffix (4.0.3)
|
39
38
|
rake (10.5.0)
|
40
|
-
redis (4.1.
|
39
|
+
redis (4.1.3)
|
41
40
|
regexp_parser (1.6.0)
|
42
41
|
rspec (3.8.0)
|
43
42
|
rspec-core (~> 3.8.0)
|
@@ -52,10 +51,10 @@ GEM
|
|
52
51
|
diff-lcs (>= 1.2.0, < 2.0)
|
53
52
|
rspec-support (~> 3.8.0)
|
54
53
|
rspec-support (3.8.0)
|
55
|
-
rubyzip (
|
56
|
-
selenium-webdriver (3.142.
|
57
|
-
childprocess (>= 0.5, <
|
58
|
-
rubyzip (
|
54
|
+
rubyzip (2.2.0)
|
55
|
+
selenium-webdriver (3.142.7)
|
56
|
+
childprocess (>= 0.5, < 4.0)
|
57
|
+
rubyzip (>= 1.2.2)
|
59
58
|
typhoeus (1.3.1)
|
60
59
|
ethon (>= 0.9.0)
|
61
60
|
watir (6.16.5)
|
@@ -67,9 +66,9 @@ GEM
|
|
67
66
|
os
|
68
67
|
psych
|
69
68
|
selenium-webdriver (>= 3.4.0)
|
70
|
-
webdrivers (4.
|
69
|
+
webdrivers (4.2.0)
|
71
70
|
nokogiri (~> 1.6)
|
72
|
-
rubyzip (
|
71
|
+
rubyzip (>= 1.3.0)
|
73
72
|
selenium-webdriver (>= 3.0, < 4.0)
|
74
73
|
|
75
74
|
PLATFORMS
|
data/lib/arachnid2/version.rb
CHANGED
data/lib/arachnid2/watir.rb
CHANGED
@@ -13,9 +13,9 @@ class Arachnid2
|
|
13
13
|
def crawl(opts)
|
14
14
|
preflight(opts)
|
15
15
|
watir_preflight
|
16
|
+
@already_retried = false
|
16
17
|
|
17
18
|
until @global_queue.empty?
|
18
|
-
@already_retried = false
|
19
19
|
q = @global_queue.shift
|
20
20
|
links = nil
|
21
21
|
|
@@ -44,13 +44,10 @@ class Arachnid2
|
|
44
44
|
yield browser
|
45
45
|
|
46
46
|
vacuum(links, browser.url)
|
47
|
+
rescue Selenium::WebDriver::Error::NoSuchWindowError, Net::ReadTimeout => e
|
47
48
|
rescue => e
|
48
|
-
next if e.class == Net::ReadTimeout
|
49
|
-
|
50
49
|
raise e if raise_before_retry?(e.class)
|
51
|
-
|
52
50
|
reset_for_retry
|
53
|
-
retry
|
54
51
|
end
|
55
52
|
|
56
53
|
end # until @global_queue.empty?
|
@@ -69,6 +66,8 @@ class Arachnid2
|
|
69
66
|
def reset_for_retry
|
70
67
|
@browser.close if @browser rescue nil
|
71
68
|
@headless.destroy if @headless rescue nil
|
69
|
+
@driver.quit if @headless rescue nil
|
70
|
+
@driver = nil
|
72
71
|
@browser = nil
|
73
72
|
@already_retried = true
|
74
73
|
end
|