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
9a32f409
Commit
9a32f409
authored
Jul 19, 2021
by
Mai Hoang Thai Ha
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
fixed ARGV
parent
8ab617be
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
9 additions
and
19 deletions
+9
-19
lib/tasks/web_crawler.rake
+9
-19
No files found.
lib/tasks/web_crawler.rake
View file @
9a32f409
require
'open-uri'
require
'open-uri'
require
'csv'
require
'csv'
require
'zip'
require
'zip'
require
"rails/all"
namespace
:crawler
do
namespace
:crawler
do
desc
'crawler from CareerBuilder'
desc
'crawler from CareerBuilder'
task
jobs: :environment
do
task
jobs: :environment
do
ARGV
.
each
{
|
a
|
task
a
.
to_sym
{
;
}
}
total_pages
=
0
total_pages
=
0
if
ARGV
.
length
<=
1
if
ARGV
.
length
==
1
&&
ARGV
[
0
]
==
'TEST'
ARGV
.
each
do
|
a
|
task
a
.
to_sym
{
;
}
case
a
when
'TEST'
total_pages
=
1
total_pages
=
1
when
'ALL'
elsif
ARGV
.
length
==
1
&&
ARGV
[
0
]
==
'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
)
jobs_per_page
=
first_page
.
css
(
'div.job-item'
).
count
jobs_per_page
=
first_page
.
css
(
'div.job-item'
).
count
total_jobs
=
first_page
.
css
(
'.search-result-list .job-found p'
).
text
.
split
(
' '
).
first
.
gsub
(
','
,
''
).
to_i
total_jobs
=
first_page
.
css
(
'.search-result-list .job-found p'
).
text
.
split
(
' '
).
first
.
gsub
(
','
,
''
).
to_i
...
@@ -23,11 +18,6 @@ namespace :crawler do
...
@@ -23,11 +18,6 @@ namespace :crawler do
else
else
exit
exit
end
end
end
elsif
# exit
exit
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
)
jobs_item
=
parsed_page
.
css
(
'div.job-item .job_link'
)
jobs_item
=
parsed_page
.
css
(
'div.job-item .job_link'
)
...
@@ -38,14 +28,13 @@ namespace :crawler do
...
@@ -38,14 +28,13 @@ namespace :crawler do
# title - company
# title - company
title
=
job_page
.
css
(
'div.job-desc h1.title'
).
text
title
=
job_page
.
css
(
'div.job-desc h1.title'
).
text
company
=
job_page
.
css
(
'div.job-desc a.job-company-name'
).
text
company
=
job_page
.
css
(
'div.job-desc a.job-company-name'
).
text
Company
.
create!
(
name:
company
)
# info box
# info box
info_box_item
=
job_detail
.
css
(
'.detail-box ul li'
)
info_box_item
=
job_detail
.
css
(
'.detail-box ul li'
)
# city, update_at, industry, type, salary, experience, level, expiration_date
# city, update_at, industry, type, salary, experience, level, expiration_date
job_industries
=
[]
job_industries
=
[]
update_at
,
job_type
,
salary
,
experience
,
level
,
expiration_date
=
''
update_at
,
job_type
,
salary
,
experience
,
level
,
expiration_date
=
''
job_cities
=
[]
job_cities
=
[]
job_detail
.
css
(
'.detail-box .map a'
).
each
do
|
part
|
job_detail
.
css
(
'.detail-box .map
p
a'
).
each
do
|
part
|
city
=
part
.
text
city
=
part
.
text
job_cities
<<
city
job_cities
<<
city
end
end
...
@@ -96,6 +85,7 @@ namespace :crawler do
...
@@ -96,6 +85,7 @@ namespace :crawler do
other_info_list
<<
info
other_info_list
<<
info
end
end
company
=
Company
.
find_or_create_by
(
name:
company
)
job
=
Job
.
find_or_create_by
(
job
=
Job
.
find_or_create_by
(
title:
title
,
title:
title
,
job_type:
job_type
,
job_type:
job_type
,
...
@@ -108,7 +98,7 @@ namespace :crawler do
...
@@ -108,7 +98,7 @@ namespace :crawler do
requirement:
requirement
,
requirement:
requirement
,
other_info:
other_info_list
.
each
{
|
info
|
}
other_info:
other_info_list
.
each
{
|
info
|
}
)
)
Company
.
find_or_initialize_by
(
name:
company
)
.
jobs
<<
job
company
.
jobs
<<
job
job_industries
.
each
do
|
industry
|
job_industries
.
each
do
|
industry
|
industry_id
=
Industry
.
find_or_create_by
(
name:
industry
)
industry_id
=
Industry
.
find_or_create_by
(
name:
industry
)
job
.
industries
<<
industry_id
job
.
industries
<<
industry_id
...
@@ -132,7 +122,7 @@ namespace :crawler do
...
@@ -132,7 +122,7 @@ namespace :crawler do
industry_list
<<
industry
industry_list
<<
industry
end
end
industry_list
.
each
do
|
industry
|
industry_list
.
each
do
|
industry
|
Industry
.
create
!
(
name:
industry
)
Industry
.
create
(
name:
industry
)
end
end
end
end
...
@@ -156,7 +146,7 @@ namespace :crawler do
...
@@ -156,7 +146,7 @@ namespace :crawler do
city_list
<<
city
city_list
<<
city
end
end
city_list
.
each
do
|
city
|
city_list
.
each
do
|
city
|
City
.
create
!
(
City
.
create
(
name:
city
[
:name
],
name:
city
[
:name
],
region:
city
[
:region
]
region:
city
[
:region
]
)
)
...
...
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