generalscraper 0.0.22 → 0.0.23
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/lib/parse_page.rb +12 -11
- 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: 85b3d91e96159d5f3cd36961664721d9bd5e7313
|
|
4
|
+
data.tar.gz: 7568e30d7343d9be690e48e0369f7cb3db194a81
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: b88b2d814a08bc24b68ed337e4e973471a57c02d1fa9323156ccd7a93f5dab754dde734e48326378e203e5c11599ee1e0be789d45eb728016feb194b0949094b
|
|
7
|
+
data.tar.gz: 5f32fd7d6da2aea69a4654a2e3e3662bcbce88412252a4b366048ffe14d02e0d33a7f57b653138b9de9eb1a7f2117cf38023072b8936a9cbd10e0e5ed7f001b7
|
data/lib/parse_page.rb
CHANGED
|
@@ -3,20 +3,21 @@ require 'uploadconvert'
|
|
|
3
3
|
module ParsePage
|
|
4
4
|
# Get both page metadata and text
|
|
5
5
|
def getPageData(url)
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
return pagehash
|
|
12
|
-
rescue
|
|
13
|
-
end
|
|
6
|
+
page = @requests.get_page(url)
|
|
7
|
+
html = Nokogiri::HTML(page)
|
|
8
|
+
pagehash = getMetadata(url, html)
|
|
9
|
+
pagehash = getContent(url, pagehash, html)
|
|
10
|
+
return pagehash
|
|
14
11
|
end
|
|
15
12
|
|
|
16
13
|
# Get the page content by type of page
|
|
17
14
|
def getContent(url, pagehash, html)
|
|
18
15
|
if url.include? ".pdf"
|
|
19
|
-
|
|
16
|
+
begin
|
|
17
|
+
return getPDF(url, pagehash)
|
|
18
|
+
rescue
|
|
19
|
+
return nil
|
|
20
|
+
end
|
|
20
21
|
else
|
|
21
22
|
return getHTMLText(url, pagehash, html)
|
|
22
23
|
end
|
|
@@ -30,7 +31,7 @@ module ParsePage
|
|
|
30
31
|
|
|
31
32
|
# Download and extract text from PDF
|
|
32
33
|
def getPDF(url, pagehash)
|
|
33
|
-
`wget -P public/uploads #{url}`
|
|
34
|
+
`wget --tries=2 -P public/uploads #{url}`
|
|
34
35
|
path = url.split("/")
|
|
35
36
|
|
|
36
37
|
# OCR PDF and save fields
|
|
@@ -51,7 +52,7 @@ module ParsePage
|
|
|
51
52
|
pagehash[:date_retrieved] = Time.now
|
|
52
53
|
|
|
53
54
|
# Get title and meta tag info
|
|
54
|
-
pagehash[:
|
|
55
|
+
pagehash[:page_title] = fixEncode(html.css("title").text)
|
|
55
56
|
html.css("meta").each do |m|
|
|
56
57
|
if m
|
|
57
58
|
pagehash[m['name']] = fixEncode(m['content'])
|