Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Contribute to GitLab
Sign in / Register
Toggle navigation
E
esi-table-data
Project
Project
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
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
esi-data-scrapping
esi-table-data
Commits
227cd025
Commit
227cd025
authored
Jun 09, 2017
by
Vasyl Bodnaruk
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add functional for store only unique news(not duplicate)
parent
eed7af2e
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
6 deletions
+5
-6
pipelines.py
exa/exa/pipelines.py
+5
-6
No files found.
exa/exa/pipelines.py
View file @
227cd025
...
...
@@ -13,9 +13,9 @@ db = get_project_settings().get('DB')
class
ExaPipeline
(
object
):
def
__init__
(
self
):
# self.out = open('out/out{}.txt'.format(datetime.now()), 'w', newline='\n')
self
.
db
=
Database
(
**
db
)
self
.
urls
=
set
(
self
.
db
.
select
(
'select url from wp_esi_accept'
))
self
.
urls
=
{
i
[
0
]
for
i
in
self
.
db
.
select
(
'select url from wp_esi_news_accept'
)}
print
(
self
.
urls
)
super
(
ExaPipeline
,
self
)
.
__init__
()
def
process_item
(
self
,
item
,
spider
):
...
...
@@ -26,11 +26,10 @@ class ExaPipeline(object):
query
=
"""INSERT INTO wp_esi_news_accept (title, description, URL, media_id, type_id, region_id, post_id,
publish_date, record_date, company_id, is_accepted) VALUES(
%
s,
%
s,
%
s,
%
s,
%
s,
%
s,
%
s,
%
s,
%
s,
%
s,
%
s);
\n
"""
print
(
item
)
n
=
self
.
db
.
select
(
"select url from wp_esi_news_accept where url={}"
.
format
(
item
[
'url'
]))
if
len
(
n
)
==
0
:
news
=
self
.
db
.
insert
(
query
,
data
)
if
item
[
'url'
]
in
self
.
urls
:
print
(
"DUPLICATE"
)
else
:
print
(
'Duplicate'
)
self
.
db
.
insert
(
query
,
data
)
# self._insert_news_entiry(news, item['company_id'])
# self.out.write(query)
...
...
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