scraper-central-ruby 1.0.0 → 1.0.2
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 +3 -1
- data/README.md +12 -0
- data/lib/proxy/base.rb +22 -2
- data/lib/scraper_central/version.rb +1 -1
- data/scraper-central-ruby.gemspec +4 -0
- metadata +16 -2
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 812034013aa0b9d1fbec3961dad038a59b3c01c26e5738b5da8ee31d0af8acd1
|
4
|
+
data.tar.gz: 2da443589638a347f9ee81a73141b43d4073bb9dd148371421b9843906886e36
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 8070123f403672e8b2f32fa6f26297447eb1f3b0bf8fcef4452b52491f82bf27fdb3e0f40a0f5e411c88372653335a94c4ed075bffa4ee6bdde589bcd1a3a4a1
|
7
|
+
data.tar.gz: 1112f3744c8c62db525394d4091e786640126a1b4a6bcaa1efa65f1ea850d5213ffcd0538df513197901d70c7f4167bf16821e1fa956e3e18be3d7bae50828ed
|
data/Gemfile.lock
CHANGED
data/README.md
CHANGED
@@ -117,6 +117,18 @@ Fetches the URL through the proxy:
|
|
117
117
|
|
118
118
|
```ruby
|
119
119
|
scraper_central = ScraperCentral.new
|
120
|
+
scraper_central.proxy_name = "BrightData"
|
121
|
+
scraper_central.cache_duration = 360
|
122
|
+
scraper_central.retry_attr = {
|
123
|
+
count: 5
|
124
|
+
}
|
125
|
+
scraper_central.s3_key = {
|
126
|
+
country: "US",
|
127
|
+
marketplace: "Amazon",
|
128
|
+
page_type: "product-question",
|
129
|
+
identifier: "B0BQZBPS4G",
|
130
|
+
page_number: 1
|
131
|
+
}
|
120
132
|
|
121
133
|
response = scraper_central.fetch("https://example.com")
|
122
134
|
|
data/lib/proxy/base.rb
CHANGED
@@ -6,6 +6,7 @@ require 'json'
|
|
6
6
|
require 'openssl'
|
7
7
|
require 'response'
|
8
8
|
require 'logger'
|
9
|
+
require 'brotli'
|
9
10
|
|
10
11
|
module Proxy
|
11
12
|
class Base
|
@@ -35,14 +36,33 @@ module Proxy
|
|
35
36
|
end
|
36
37
|
|
37
38
|
def format_response(response)
|
39
|
+
if response.kind_of?(Net::HTTPSuccess) && response.header['Content-Encoding'].eql?('gzip')
|
40
|
+
sio = StringIO.new(response.body)
|
41
|
+
gz = Zlib::GzipReader.new(sio)
|
42
|
+
page_content = gz.read()
|
43
|
+
elsif response.kind_of?(Net::HTTPSuccess) && response.header['Content-Encoding'].eql?('br')
|
44
|
+
# Decode response which is in brotli encryption and save it as html
|
45
|
+
page_content = Brotli.inflate(response.body)
|
46
|
+
else
|
47
|
+
page_content = response.body
|
48
|
+
end
|
49
|
+
|
38
50
|
Response.new(
|
39
51
|
code: response.code.to_i,
|
40
|
-
body:
|
41
|
-
headers: response
|
52
|
+
body: page_content,
|
53
|
+
headers: get_headers(response),
|
42
54
|
cookies: response.get_fields('set-cookie')
|
43
55
|
)
|
44
56
|
end
|
45
57
|
|
58
|
+
def get_headers(response)
|
59
|
+
headers = {}
|
60
|
+
response.each_header do |key, value|
|
61
|
+
headers[key] = value
|
62
|
+
end
|
63
|
+
headers
|
64
|
+
end
|
65
|
+
|
46
66
|
def prepare_request(uri, proxy_uri = nil)
|
47
67
|
http = if proxy_uri.nil?
|
48
68
|
Net::HTTP.new(uri.host, uri.port)
|
@@ -14,6 +14,10 @@ Gem::Specification.new do |spec|
|
|
14
14
|
spec.homepage = 'https://github.com/patterninc/scraper-central-ruby'
|
15
15
|
spec.license = 'MIT'
|
16
16
|
|
17
|
+
|
18
|
+
# Add the brotli gem dependency here
|
19
|
+
spec.add_dependency 'brotli', '~> 0.5.0'
|
20
|
+
|
17
21
|
# Specify which files should be added to the gem when it is released.
|
18
22
|
# The `git ls-files -z` loads the files in the RubyGem that have been added into git.
|
19
23
|
spec.files = Dir.chdir(File.expand_path(__dir__)) do
|
metadata
CHANGED
@@ -1,15 +1,29 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: scraper-central-ruby
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 1.0.
|
4
|
+
version: 1.0.2
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Patterninc
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-07-
|
11
|
+
date: 2024-07-19 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: brotli
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: 0.5.0
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: 0.5.0
|
13
27
|
- !ruby/object:Gem::Dependency
|
14
28
|
name: bundler
|
15
29
|
requirement: !ruby/object:Gem::Requirement
|