email_crawler 0.0.10 → 0.0.11
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/bin/email-crawler +7 -0
- data/lib/email_crawler/version.rb +1 -1
- data/lib/email_crawler.rb +5 -2
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: c1d4c2e2b7fa2781a050534296a5de7783100c3a
|
|
4
|
+
data.tar.gz: 5fd71c35a51c903284312217e1195e807f1e2d40
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 2ac69d6d4042db503c947b303e0b1cb28ea3421e0c11879f18652d734f865adee341dcc3cfae2bc98ff7f46c8e7389c55c5b6884aa6690e63c2b1163c69c50c3
|
|
7
|
+
data.tar.gz: ce1d9e1f24b7488aac88f68fa75003d28065cd5c12917435c7221cb2901d6b99507613eb473f719929f314a4e9c5b8ace850fef3fb19f1fa58619f99721741e0
|
data/bin/email-crawler
CHANGED
|
@@ -12,6 +12,7 @@ class OptionsParser
|
|
|
12
12
|
options.max_results = ::EmailCrawler::Scraper::MAX_RESULTS
|
|
13
13
|
options.max_links = ::EmailCrawler::PageLinks::MAX_LINKS
|
|
14
14
|
options.max_concurrency = ::EmailCrawler::Runner::MAX_CONCURRENCY
|
|
15
|
+
options.blacklisted_domains = []
|
|
15
16
|
|
|
16
17
|
opt_parser = OptionParser.new do |opts|
|
|
17
18
|
opts.banner = "Usage: email-crawler [options]"
|
|
@@ -45,6 +46,11 @@ class OptionsParser
|
|
|
45
46
|
" (defaults to 10)") do |max_concurrency|
|
|
46
47
|
options.max_concurrency = max_concurrency.to_i
|
|
47
48
|
end
|
|
49
|
+
|
|
50
|
+
opts.on("-b", "--blacklist DOMAIN",
|
|
51
|
+
"Blacklist URLs under this domain from Google's search results") do |domain|
|
|
52
|
+
options.blacklisted_domains << domain
|
|
53
|
+
end
|
|
48
54
|
end
|
|
49
55
|
|
|
50
56
|
opt_parser.parse!(args)
|
|
@@ -61,6 +67,7 @@ else
|
|
|
61
67
|
runner.max_results = options.max_results
|
|
62
68
|
runner.max_links = options.max_links
|
|
63
69
|
runner.max_concurrency = options.max_concurrency
|
|
70
|
+
runner.blacklisted_domains = options.blacklisted_domains
|
|
64
71
|
end
|
|
65
72
|
csv = runner.run(options.q)
|
|
66
73
|
$stdout << "#{csv}\n"
|
data/lib/email_crawler.rb
CHANGED
|
@@ -14,7 +14,7 @@ module EmailCrawler
|
|
|
14
14
|
class Runner
|
|
15
15
|
MAX_CONCURRENCY = 50
|
|
16
16
|
|
|
17
|
-
attr_writer :max_results, :max_links, :max_concurrency, :logger
|
|
17
|
+
attr_writer :max_results, :max_links, :max_concurrency, :logger, :blacklisted_domains
|
|
18
18
|
|
|
19
19
|
def initialize(google_website)
|
|
20
20
|
@google_website = google_website
|
|
@@ -22,7 +22,10 @@ module EmailCrawler
|
|
|
22
22
|
end
|
|
23
23
|
|
|
24
24
|
def run(q)
|
|
25
|
-
urls = Scraper.new(@google_website,
|
|
25
|
+
urls = Scraper.new(@google_website,
|
|
26
|
+
max_results: @max_results,
|
|
27
|
+
blacklisted_domains: @blacklisted_domains).
|
|
28
|
+
search_result_urls_for(q)
|
|
26
29
|
urls.each { |url| logger.info "#{url}" }
|
|
27
30
|
queue = Queue.new
|
|
28
31
|
urls.each { |url| queue.push(url) }
|