Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
V
VenJob
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
Mai Hoang Thai Ha
VenJob
Commits
b8abb807
Commit
b8abb807
authored
Jul 27, 2021
by
Mai Hoang Thai Ha
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add logger
parent
8328deb3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
9 additions
and
3 deletions
+9
-3
db/migrate/20210706092230_create_jobs.rb
+1
-1
db/schema.rb
+1
-1
lib/tasks/web_crawler.rake
+7
-1
No files found.
db/migrate/20210706092230_create_jobs.rb
View file @
b8abb807
class
CreateJobs
<
ActiveRecord
::
Migration
[
6.1
]
class
CreateJobs
<
ActiveRecord
::
Migration
[
6.1
]
def
change
def
change
create_table
:jobs
do
|
t
|
create_table
:jobs
do
|
t
|
t
.
string
:title
t
.
string
:title
,
null:
false
t
.
string
:job_type
t
.
string
:job_type
t
.
string
:salary
t
.
string
:salary
t
.
string
:experience
t
.
string
:experience
...
...
db/schema.rb
View file @
b8abb807
...
@@ -105,7 +105,7 @@ ActiveRecord::Schema.define(version: 2021_07_20_055614) do
...
@@ -105,7 +105,7 @@ ActiveRecord::Schema.define(version: 2021_07_20_055614) do
end
end
create_table
"jobs"
,
charset:
"utf8mb4"
,
collation:
"utf8mb4_0900_ai_ci"
,
force: :cascade
do
|
t
|
create_table
"jobs"
,
charset:
"utf8mb4"
,
collation:
"utf8mb4_0900_ai_ci"
,
force: :cascade
do
|
t
|
t
.
string
"title"
t
.
string
"title"
,
null:
false
t
.
string
"job_type"
t
.
string
"job_type"
t
.
string
"salary"
t
.
string
"salary"
t
.
string
"experience"
t
.
string
"experience"
...
...
lib/tasks/web_crawler.rake
View file @
b8abb807
...
@@ -7,6 +7,8 @@ namespace :crawler do
...
@@ -7,6 +7,8 @@ namespace :crawler do
unless
%w[ALL TEST]
.
include?
(
ENV
[
'TYPE'
])
unless
%w[ALL TEST]
.
include?
(
ENV
[
'TYPE'
])
abort
'Do you want to crawl all pages (ALL) or some pages (TEST)? Please ONLY pass ONE argument.'
abort
'Do you want to crawl all pages (ALL) or some pages (TEST)? Please ONLY pass ONE argument.'
end
end
logger
=
Logger
.
new
(
"
#{
Rails
.
root
}
/log/job_crawler.log"
)
logger
.
info
"Start crawler job at:
#{
Time
.
current
}
"
total_pages
=
5
# default = TEST
total_pages
=
5
# default = TEST
if
ENV
[
'TYPE'
]
==
'ALL'
if
ENV
[
'TYPE'
]
==
'ALL'
first_page
=
Nokogiri
::
HTML
(
HTTParty
.
get
(
'https://careerbuilder.vn/viec-lam/tat-ca-viec-lam-vi.html'
).
body
)
first_page
=
Nokogiri
::
HTML
(
HTTParty
.
get
(
'https://careerbuilder.vn/viec-lam/tat-ca-viec-lam-vi.html'
).
body
)
...
@@ -16,10 +18,12 @@ namespace :crawler do
...
@@ -16,10 +18,12 @@ namespace :crawler do
end
end
(
1
..
total_pages
).
each
do
|
page
|
(
1
..
total_pages
).
each
do
|
page
|
parsed_page
=
Nokogiri
::
HTML
(
HTTParty
.
get
(
"https://careerbuilder.vn/viec-lam/tat-ca-viec-lam-trang-
#{
page
}
-vi.html"
).
body
)
parsed_page
=
Nokogiri
::
HTML
(
HTTParty
.
get
(
"https://careerbuilder.vn/viec-lam/tat-ca-viec-lam-trang-
#{
page
}
-vi.html"
).
body
)
logger
.
info
(
"Page:
#{
page
}
"
)
jobs_item
=
parsed_page
.
css
(
'div.job-item .job_link'
)
jobs_item
=
parsed_page
.
css
(
'div.job-item .job_link'
)
jobs_item
.
each
do
|
item
|
jobs_item
.
each
do
|
item
|
retries
||=
0
retries
||=
0
url
||=
item
.
attribute
(
'href'
).
text
url
||=
item
.
attribute
(
'href'
).
text
logger
.
info
(
"job link:
#{
url
}
"
)
job_page
=
Nokogiri
::
HTML
(
HTTParty
.
get
(
url
).
body
)
job_page
=
Nokogiri
::
HTML
(
HTTParty
.
get
(
url
).
body
)
# Job
# Job
job_title
=
job_page
.
css
(
'div.job-desc h1.title'
).
text
job_title
=
job_page
.
css
(
'div.job-desc h1.title'
).
text
...
@@ -88,6 +92,7 @@ namespace :crawler do
...
@@ -88,6 +92,7 @@ namespace :crawler do
job_object
.
cities
<<
city_objects
job_object
.
cities
<<
city_objects
rescue
URI
::
InvalidURIError
=>
e
rescue
URI
::
InvalidURIError
=>
e
puts
"[Error]
#{
e
.
message
}
"
puts
"[Error]
#{
e
.
message
}
"
logger
.
error
"URI must be ascii only :
#{
url
}
"
encode_url
=
CGI
.
escape
(
url
.
remove
(
'https://careerbuilder.vn/vi/tim-viec-lam/'
))
encode_url
=
CGI
.
escape
(
url
.
remove
(
'https://careerbuilder.vn/vi/tim-viec-lam/'
))
url
=
"https://careerbuilder.vn/vi/tim-viec-lam/
#{
encode_url
}
"
url
=
"https://careerbuilder.vn/vi/tim-viec-lam/
#{
encode_url
}
"
retry
if
(
retries
+=
1
)
<
2
retry
if
(
retries
+=
1
)
<
2
...
@@ -96,6 +101,7 @@ namespace :crawler do
...
@@ -96,6 +101,7 @@ namespace :crawler do
puts
e
.
backtrace
.
inspect
puts
e
.
backtrace
.
inspect
end
end
end
end
logger
.
info
"Finished at:
#{
Time
.
current
}
"
end
end
desc
'crawler industry form CareerBuilder'
desc
'crawler industry form CareerBuilder'
...
@@ -110,7 +116,7 @@ namespace :crawler do
...
@@ -110,7 +116,7 @@ namespace :crawler do
desc
'crawler city form CareerBuilder'
desc
'crawler city form CareerBuilder'
task
cities: :environment
do
task
cities: :environment
do
parsed_page
||
=
Nokogiri
::
HTML
(
HTTParty
.
get
(
'https://careerbuilder.vn/tim-viec-lam.html'
).
body
)
parsed_page
=
Nokogiri
::
HTML
(
HTTParty
.
get
(
'https://careerbuilder.vn/tim-viec-lam.html'
).
body
)
list_location
=
parsed_page
.
css
(
'div.main-jobs-by-location ul li'
)
list_location
=
parsed_page
.
css
(
'div.main-jobs-by-location ul li'
)
list_location
.
each
do
|
city
|
list_location
.
each
do
|
city
|
city_name
=
city
.
text
city_name
=
city
.
text
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment