apollo-crawler 0.1.27 → 0.1.28
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
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 22e840b1ad9ecabcb011c4b02383c060d325a61f
|
4
|
+
data.tar.gz: faf47f1ae1b7451262037d7c3e28a83bb05a2678
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: f916c2da81657168389ddf998407d338bbdafd323dfb5b7f0e3b4dc9ef2e9d001d00974fee48d2918a12762a90e5172146820553b09d798720f33c319db052a7
|
7
|
+
data.tar.gz: a820bf980c655156eefcad5487a79805f121f7e59d2e95285415d0229583b3df4440a4c0e8021186fc963837239cd0b1a9c1e8ca18718dc5db67bc54ff6ce9a7
|
@@ -90,6 +90,8 @@ module Apollo
|
|
90
90
|
declarations[:queues]["planner.crawled.queue"].bind(declarations[:exchanges]["planner.crawled"]).subscribe do |delivery_info, metadata, payload|
|
91
91
|
msg = JSON.parse(payload)
|
92
92
|
|
93
|
+
puts "Crawled - msg.inspect"
|
94
|
+
|
93
95
|
request = msg['request']
|
94
96
|
response = msg['response']
|
95
97
|
data = msg['data']
|
@@ -122,7 +124,8 @@ module Apollo
|
|
122
124
|
|
123
125
|
def get_next_url(opts={})
|
124
126
|
tmp = Apollo::Model::QueuedUrl.where({:state => :queued}).order_by(:created_at.asc)
|
125
|
-
tmp.find_and_modify({ "$set" => { state: :fetching }}, new: true)
|
127
|
+
res = tmp.find_and_modify({ "$set" => { state: :fetching }}, new: true)
|
128
|
+
return res
|
126
129
|
end
|
127
130
|
|
128
131
|
def fetch_queued_urls(opts={})
|
@@ -26,7 +26,9 @@ module Apollo
|
|
26
26
|
def self.schedule(url, crawler=nil, opts={})
|
27
27
|
queued_url = Apollo::Model::QueuedUrl.where(:url => url).first
|
28
28
|
|
29
|
-
|
29
|
+
if queued_url.nil? == false
|
30
|
+
return queued_url
|
31
|
+
end
|
30
32
|
|
31
33
|
res = Apollo::Model::QueuedUrl.new(:url => url, :state => :queued, :crawler_name => crawler.to_s)
|
32
34
|
res.save
|