Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
gargantext
Project
Project
Details
Activity
Releases
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
humanities
gargantext
Commits
91ad791f
Commit
91ad791f
authored
Aug 10, 2017
by
sim
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
[FIX] Fix pubmed and istex crawling in newCorpus
parent
9d49e6c1
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
30 additions
and
5 deletions
+30
-5
gargantext_notebook.py
install/notebook/gargantext_notebook.py
+30
-5
No files found.
install/notebook/gargantext_notebook.py
View file @
91ad791f
...
@@ -118,7 +118,11 @@ def get_moissonneur(name):
...
@@ -118,7 +118,11 @@ def get_moissonneur(name):
""" Return moissonneur module from its name """
""" Return moissonneur module from its name """
if
not
isinstance
(
name
,
str
)
or
not
name
.
islower
():
if
not
isinstance
(
name
,
str
)
or
not
name
.
islower
():
raise
NotebookError
(
"Invalid moissonneur name:
%
r"
%
name
)
raise
NotebookError
(
"Invalid moissonneur name:
%
r"
%
name
)
return
importlib
.
import_module
(
'moissonneurs.
%
s'
%
name
)
module
=
importlib
.
import_module
(
'moissonneurs.
%
s'
%
name
)
module
.
name
=
name
return
module
def
run_moissonneur
(
moissonneur
,
project
,
name
,
query
):
def
run_moissonneur
(
moissonneur
,
project
,
name
,
query
):
...
@@ -135,12 +139,33 @@ def run_moissonneur(moissonneur, project, name, query):
...
@@ -135,12 +139,33 @@ def run_moissonneur(moissonneur, project, name, query):
request
.
POST
=
{
'string'
:
name
,
request
.
POST
=
{
'string'
:
name
,
'query'
:
query
,
'query'
:
query
,
'N'
:
QUERY_SIZE_N_MAX
}
'N'
:
QUERY_SIZE_N_MAX
}
request
.
user
=
(
session
.
query
(
UserNode
)
.
join
(
User
)
request
.
user
=
Dummy
()
.
filter
(
User
.
username
==
'gargantua'
)
.
first
())
request
.
user
.
id
=
project
.
user_id
request
.
user
.
is_authenticated
=
lambda
:
True
if
moissonneur
.
name
==
'istex'
:
# Replace ALL spaces by plus signs
request
.
POST
[
'query'
]
=
'+'
.
join
(
filter
(
None
,
query
.
split
(
' '
)))
try
:
try
:
moissonneur
.
query
(
request
)
import
json
corpus
=
moissonneur
.
save
(
request
,
project
.
id
,
return_corpus
=
True
)
r
=
moissonneur
.
query
(
request
)
raw_json
=
r
.
content
.
decode
(
'utf-8'
)
data
=
json
.
loads
(
raw_json
)
if
moissonneur
.
name
==
'pubmed'
:
count
=
sum
(
x
[
'count'
]
for
x
in
data
)
request
.
POST
[
'query'
]
=
raw_json
elif
moissonneur
.
name
==
'istex'
:
count
=
data
.
get
(
'total'
,
0
)
else
:
count
=
data
.
get
(
'results_nb'
,
0
)
if
count
>
0
:
corpus
=
moissonneur
.
save
(
request
,
project
.
id
,
return_corpus
=
True
)
else
:
return
None
except
(
ValueError
,
Http404
)
as
e
:
except
(
ValueError
,
Http404
)
as
e
:
raise
e
raise
e
...
...
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