spider 0.6.0 → 0.7.0
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/VERSION +1 -1
- data/lib/spider/spider_instance.rb +24 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 7286f875f41881c9c8c385987c322b9832e5b07c6147aa4910a900e59015927e
|
|
4
|
+
data.tar.gz: 145ecd718a34521c17f0f9e939cb66f964ca0a1f93533969caf7d54426b213a8
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: ba771c7dbbe3df286475a5586ba2d2b63affe762b7bf504694e6865e39c8e7f5047811ac97285a1edc5d99cd478993fd2be9ee3ae244cc1690975f7ab3f0e779
|
|
7
|
+
data.tar.gz: 2bd17f25db36a267b5534ff663b8394e7439a1701970e6d23ea295818732133b23c4bb35f82aa1f6f90022edcaceafc47b3fee3f7902fd9028a2ec8ad697a2a4
|
data/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
0.
|
|
1
|
+
0.7.0
|
|
@@ -260,11 +260,34 @@ class SpiderInstance
|
|
|
260
260
|
end
|
|
261
261
|
|
|
262
262
|
def generate_next_urls(a_url, resp) #:nodoc:
|
|
263
|
+
# Only scan for links if the content-type is HTML or the URL ends with .html
|
|
264
|
+
content_type = resp['Content-Type'] || resp['content-type'] || ''
|
|
265
|
+
url_ends_with_html = a_url.downcase.end_with?('.html')
|
|
266
|
+
|
|
267
|
+
unless content_type.downcase.include?('text/html') || url_ends_with_html
|
|
268
|
+
return []
|
|
269
|
+
end
|
|
270
|
+
|
|
263
271
|
web_page = resp.body
|
|
264
272
|
base_url = (web_page.scan(/base\s+href="(.*?)"/i).flatten +
|
|
265
273
|
[a_url[0,a_url.rindex('/')]])[0]
|
|
266
274
|
base_url = remove_trailing_slash(base_url)
|
|
267
|
-
|
|
275
|
+
|
|
276
|
+
# Extract anchor tags with href attributes, respecting rel="nofollow"
|
|
277
|
+
web_page.scan(/<a\s[^>]*href="([^"]*)"[^>]*>/i).flatten.map do |link|
|
|
278
|
+
# Get the full anchor tag to check for rel attribute
|
|
279
|
+
anchor_match = web_page.match(/<a\s[^>]*href="#{Regexp.escape(link)}"[^>]*>/i)
|
|
280
|
+
next nil unless anchor_match
|
|
281
|
+
|
|
282
|
+
anchor_tag = anchor_match[0]
|
|
283
|
+
|
|
284
|
+
# Check if this link has rel="nofollow" or similar attributes that should be respected
|
|
285
|
+
if anchor_tag.match(/rel\s*=\s*["']([^"']*nofollow[^"']*)["']/i) ||
|
|
286
|
+
anchor_tag.match(/rel\s*=\s*["']([^"']*sponsored[^"']*)["']/i) ||
|
|
287
|
+
anchor_tag.match(/rel\s*=\s*["']([^"']*ugc[^"']*)["']/i)
|
|
288
|
+
next nil # Skip links with nofollow, sponsored, or ugc rel attributes
|
|
289
|
+
end
|
|
290
|
+
|
|
268
291
|
begin
|
|
269
292
|
parsed_link = URI.parse(link)
|
|
270
293
|
if parsed_link.fragment == '#'
|