zeitungen 0.2.3 → 0.2.4
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/.gitignore +3 -1
- data/lib/zeitungen.rb +1 -0
- data/lib/zeitungen/downloader.rb +32 -9
- data/lib/zeitungen/version.rb +1 -1
- data/zeitungen.gemspec +1 -0
- metadata +16 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 7f0b320e2eb2f2e765162d7e7ea1785ed34dd360
|
|
4
|
+
data.tar.gz: a596e27b09d564b4ec625057cc36734fd086f74d
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: fae374fd14e3b047743719995a2058babeb5b7e7dbe4b2c4fdf373274040c56c8e5a1ff701762cbf6477413859f343059a3b971b87fc764770cae7bd8fc016b9
|
|
7
|
+
data.tar.gz: 15d3c52e0f960b11812d84869077804dac613bc40622ad5d2121f465310ee8c297c7d8e84ecb061b5e86a95c8b0aff5f1658703309da3986cee85d8b9f2c88f5
|
data/.gitignore
CHANGED
data/lib/zeitungen.rb
CHANGED
data/lib/zeitungen/downloader.rb
CHANGED
|
@@ -1,10 +1,11 @@
|
|
|
1
1
|
module Zeitungen
|
|
2
2
|
class Downloader
|
|
3
|
-
def initialize(url, zeitungen, client, passwords)
|
|
3
|
+
def initialize(url, zeitungen, client, passwords, verbose: false)
|
|
4
4
|
@url = url
|
|
5
|
-
@zeitungen
|
|
5
|
+
@zeitungen = zeitungen
|
|
6
6
|
@client = client
|
|
7
7
|
@passwords = passwords
|
|
8
|
+
@verbose = verbose
|
|
8
9
|
end
|
|
9
10
|
|
|
10
11
|
def run(date=Date.today, options={})
|
|
@@ -14,6 +15,7 @@ module Zeitungen
|
|
|
14
15
|
|
|
15
16
|
page = IndexPage.new(@url, @passwords)
|
|
16
17
|
zeitungen_links = page.links(date)
|
|
18
|
+
puts "zeitungen_links.size: #{zeitungen_links.size}" if @verbose
|
|
17
19
|
# puts zeitungen_links.inspect
|
|
18
20
|
queue = enqueue(zeitungen_links)
|
|
19
21
|
|
|
@@ -37,9 +39,12 @@ module Zeitungen
|
|
|
37
39
|
@zeitungen.each do |z|
|
|
38
40
|
if link = zeitungen_links.find{|l| z.regexp.match l.text } # se c'è un link per il zeitungen corrente
|
|
39
41
|
uri = link.uri
|
|
42
|
+
puts "uri: #{uri}" if @verbose
|
|
40
43
|
if uri.host=="t.umblr.com"
|
|
41
44
|
h = Hash[uri.query.split("&").map{|e| e.split("=")}]
|
|
42
|
-
|
|
45
|
+
u = URI(URI.unescape(h["z"])+"\?directDownload\=true")
|
|
46
|
+
puts "u: #{u}" if @verbose
|
|
47
|
+
z.uri = u
|
|
43
48
|
else
|
|
44
49
|
z.uri = uri+"\?directDownload\=true" # zeitungen.uri+"\?directDownload\=true"
|
|
45
50
|
end
|
|
@@ -56,14 +61,32 @@ module Zeitungen
|
|
|
56
61
|
Thread.new do
|
|
57
62
|
while !queue.empty? && z = queue.pop
|
|
58
63
|
begin
|
|
59
|
-
|
|
64
|
+
url = z.uri
|
|
60
65
|
file = Tempfile.new('zeitungen')
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
+
|
|
67
|
+
|
|
68
|
+
res = HTTP.get(url)
|
|
69
|
+
i = 0
|
|
70
|
+
puts "Response status: #{res.status.to_s}" if @verbose
|
|
71
|
+
while res.status.to_s=="302 Found" and i<5 # max 5 redirect
|
|
72
|
+
url = res.headers.get("Location")
|
|
73
|
+
url = url.first if url.is_a? Array
|
|
74
|
+
puts "Redirect URL: #{url}" if @verbose
|
|
75
|
+
res = HTTP.get(url)
|
|
76
|
+
puts "Response status: #{res.status.to_s}" if @verbose
|
|
77
|
+
i += 1
|
|
66
78
|
end
|
|
79
|
+
puts "downloading #{z.final_name} (#{url})..."
|
|
80
|
+
file.write(res.to_s)
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
# res = HTTP.get()
|
|
84
|
+
# Net::HTTP.start(uri.host, uri.port, use_ssl: uri.scheme=='https') do |http|
|
|
85
|
+
# request = Net::HTTP::Get.new(uri)
|
|
86
|
+
# puts "downloading #{z.final_name} (#{z.uri})..."
|
|
87
|
+
# response = http.request request
|
|
88
|
+
# file.write(response.body)
|
|
89
|
+
# end
|
|
67
90
|
|
|
68
91
|
filename = filename_w_date(z.final_name)
|
|
69
92
|
z.upload ? @client.mv_file_in_public_dest(filename, file) : @client.mv_file_in_private_dest(filename, file)
|
data/lib/zeitungen/version.rb
CHANGED
data/zeitungen.gemspec
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: zeitungen
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.2.
|
|
4
|
+
version: 0.2.4
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Iwan Buetti
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2016-
|
|
11
|
+
date: 2016-06-23 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: bundler
|
|
@@ -178,6 +178,20 @@ dependencies:
|
|
|
178
178
|
- - ">="
|
|
179
179
|
- !ruby/object:Gem::Version
|
|
180
180
|
version: '0'
|
|
181
|
+
- !ruby/object:Gem::Dependency
|
|
182
|
+
name: http
|
|
183
|
+
requirement: !ruby/object:Gem::Requirement
|
|
184
|
+
requirements:
|
|
185
|
+
- - ">="
|
|
186
|
+
- !ruby/object:Gem::Version
|
|
187
|
+
version: '0'
|
|
188
|
+
type: :runtime
|
|
189
|
+
prerelease: false
|
|
190
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
191
|
+
requirements:
|
|
192
|
+
- - ">="
|
|
193
|
+
- !ruby/object:Gem::Version
|
|
194
|
+
version: '0'
|
|
181
195
|
description:
|
|
182
196
|
email:
|
|
183
197
|
- iwan.buetti@gmail.com
|