email_crawler 0.0.7 → 0.0.8
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/README.md +1 -1
- data/lib/email_crawler/version.rb +1 -1
- data/lib/email_crawler.rb +2 -2
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: aadbe92dd2c7670e25d389a5008badaae8334fc0
|
|
4
|
+
data.tar.gz: 265adbfb7bb28397ff93af922ddd670044b2f2a6
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 0c2eb98801a94251434c1c009a357552813c0f3734d999f5b29c740f5419756561d97ef5b30c22472c1eaacf0cc37bfde835e47502b516d4a45232cdff8a846b
|
|
7
|
+
data.tar.gz: 607749a5ce4831fcbd929721f09191f3e2d4f10d93485fc41c92577b5250c2d480b1b1138493ce18519e30969a91ab0e101c7300f31a59ef0482b598589b7935
|
data/README.md
CHANGED
|
@@ -40,7 +40,7 @@ email-crawler --query "berlin walks" --max-results 250
|
|
|
40
40
|
email-crawler --query "berlin walks" --max-links 250
|
|
41
41
|
```
|
|
42
42
|
|
|
43
|
-
* Specify how many threads to use when searching for links and email addresses (defaults to
|
|
43
|
+
* Specify how many threads to use when searching for links and email addresses (defaults to 50)
|
|
44
44
|
|
|
45
45
|
```bash
|
|
46
46
|
email-crawler --query "berlin walks" --concurrency 25
|
data/lib/email_crawler.rb
CHANGED
|
@@ -12,7 +12,7 @@ require_relative "email_crawler/email_scanner"
|
|
|
12
12
|
|
|
13
13
|
module EmailCrawler
|
|
14
14
|
class Runner
|
|
15
|
-
MAX_CONCURRENCY =
|
|
15
|
+
MAX_CONCURRENCY = 50
|
|
16
16
|
|
|
17
17
|
attr_writer :max_results, :max_links, :max_concurrency
|
|
18
18
|
|
|
@@ -62,7 +62,7 @@ module EmailCrawler
|
|
|
62
62
|
|
|
63
63
|
links_by_url.each { |arr| queue.push(arr) }
|
|
64
64
|
emails_by_url = ThreadSafe::Hash.new
|
|
65
|
-
threads = (1..[links_by_url.length,
|
|
65
|
+
threads = (1..[links_by_url.length, @max_concurrency].min).map do |i|
|
|
66
66
|
Thread.new(i) do |i|
|
|
67
67
|
arr = begin
|
|
68
68
|
queue.pop(true)
|
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: email_crawler
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.0.
|
|
4
|
+
version: 0.0.8
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Cristian Rasch
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2014-03-
|
|
11
|
+
date: 2014-03-21 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: mechanize
|