generalscraper 0.0.4 → 0.0.5
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 +3 -3
- 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: 21df27ba7416ab3ea410f3c38f0aea43cfa0c5f0
|
|
4
|
+
data.tar.gz: bbdfaa98d9c7c0600dc626b43da0127a43472b36
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: f9c37e1e151b37d4eb231fb22304d9f7868eed8a02cb874aa9968756be0f2ad2f555f36c2e8a02977c353579232c6c7a40ee776236ec425e2bef28959f6ce80a
|
|
7
|
+
data.tar.gz: 57d4a622ed823a0acad91bea00a787e2f341721ed110c3d5a88b93f9c981e267a14d62a0db1c71993a10dd9042d77496833724a5f893123288b15f9d9faf9223
|
data/lib/parse_page.rb
CHANGED
|
@@ -23,7 +23,7 @@ module ParsePage
|
|
|
23
23
|
# Download the page text
|
|
24
24
|
def getHTMLText(url, pagehash)
|
|
25
25
|
html = Nokogiri::HTML(getPage(url).body)
|
|
26
|
-
pagehash[:text] = html.css("body").text
|
|
26
|
+
pagehash[:text] = html.css("body").text.encode("UTF-8")
|
|
27
27
|
return pagehash
|
|
28
28
|
end
|
|
29
29
|
|
|
@@ -35,7 +35,7 @@ module ParsePage
|
|
|
35
35
|
# OCR PDF and save fields
|
|
36
36
|
u = UploadConvert.new("public/uploads/" + path[path.length-1].chomp.strip)
|
|
37
37
|
pdfparse = JSON.parse(u.handleDoc)
|
|
38
|
-
pdfparse.each{|k, v| pagehash[k] = v}
|
|
38
|
+
pdfparse.each{|k, v| pagehash[k] = v.encode("UTF-8")}
|
|
39
39
|
return pagehash
|
|
40
40
|
end
|
|
41
41
|
|
|
@@ -51,7 +51,7 @@ module ParsePage
|
|
|
51
51
|
|
|
52
52
|
# Get title and meta tag info
|
|
53
53
|
html = Nokogiri::HTML(getPage(url).body) # Eventually modify this
|
|
54
|
-
pagehash[:title] = html.css("title").text
|
|
54
|
+
pagehash[:title] = html.css("title").text.encode("UTF-8")
|
|
55
55
|
html.css("meta").each do |m|
|
|
56
56
|
if m
|
|
57
57
|
pagehash[m['name']] = m['content']
|