Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Sign in / Register
Toggle navigation
T
Twint
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Locked Files
Issues
0
Issues
0
List
Boards
Labels
Service Desk
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Security & Compliance
Security & Compliance
Dependency List
License Compliance
Packages
Packages
List
Container Registry
Analytics
Analytics
CI / CD
Code Review
Insights
Issues
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
nanahira
Twint
Commits
2348211b
Commit
2348211b
authored
Oct 29, 2020
by
Chris Partridge
Committed by
GitHub
Oct 29, 2020
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Fixes Publishing Data to Elasticsearch (#994)
* Fix ES publishing * Remove hour() from elasticsearch.py
parent
52ee7522
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
13 additions
and
21 deletions
+13
-21
twint/storage/elasticsearch.py
twint/storage/elasticsearch.py
+12
-19
twint/storage/panda.py
twint/storage/panda.py
+1
-2
No files found.
twint/storage/elasticsearch.py
View file @
2348211b
## TODO - Fix Weekday situation
## TODO - Fix Weekday situation
from
elasticsearch
import
Elasticsearch
,
helpers
from
elasticsearch
import
Elasticsearch
,
helpers
from
geopy.geocoders
import
Nominatim
from
geopy.geocoders
import
Nominatim
from
time
import
strftime
,
local
time
from
datetime
import
date
time
import
contextlib
import
contextlib
import
sys
import
sys
...
@@ -58,7 +58,7 @@ def createIndex(config, instance, **scope):
...
@@ -58,7 +58,7 @@ def createIndex(config, instance, **scope):
"properties"
:
{
"properties"
:
{
"id"
:
{
"type"
:
"long"
},
"id"
:
{
"type"
:
"long"
},
"conversation_id"
:
{
"type"
:
"long"
},
"conversation_id"
:
{
"type"
:
"long"
},
"created_at"
:
{
"type"
:
"
long
"
},
"created_at"
:
{
"type"
:
"
text
"
},
"date"
:
{
"type"
:
"date"
,
"format"
:
"yyyy-MM-dd HH:mm:ss"
},
"date"
:
{
"type"
:
"date"
,
"format"
:
"yyyy-MM-dd HH:mm:ss"
},
"timezone"
:
{
"type"
:
"keyword"
},
"timezone"
:
{
"type"
:
"keyword"
},
"place"
:
{
"type"
:
"keyword"
},
"place"
:
{
"type"
:
"keyword"
},
...
@@ -193,25 +193,18 @@ def weekday(day):
...
@@ -193,25 +193,18 @@ def weekday(day):
return
weekdays
[
day
]
return
weekdays
[
day
]
def
hour
(
datetime
):
return
strftime
(
"
%
H"
,
localtime
(
datetime
))
def
Tweet
(
Tweet
,
config
):
def
Tweet
(
Tweet
,
config
):
global
_index_tweet_status
global
_index_tweet_status
global
_is_near_def
global
_is_near_def
weekdays
=
{
date_obj
=
datetime
.
strptime
(
Tweet
.
datetime
,
"
%
Y-
%
m-
%
d
%
H:
%
M:
%
S
%
Z"
)
"Monday"
:
1
,
"Tuesday"
:
2
,
"Wednesday"
:
3
,
"Thursday"
:
4
,
"Friday"
:
5
,
"Saturday"
:
6
,
"Sunday"
:
7
,
}
day
=
weekdays
[
strftime
(
"
%
A"
,
localtime
(
Tweet
.
datetime
/
1000
))]
actions
=
[]
actions
=
[]
try
:
retweet
=
Tweet
.
retweet
except
AttributeError
:
retweet
=
None
dt
=
f
"{Tweet.datestamp} {Tweet.timestamp}"
dt
=
f
"{Tweet.datestamp} {Tweet.timestamp}"
j_data
=
{
j_data
=
{
...
@@ -231,10 +224,10 @@ def Tweet(Tweet, config):
...
@@ -231,10 +224,10 @@ def Tweet(Tweet, config):
"user_id_str"
:
Tweet
.
user_id_str
,
"user_id_str"
:
Tweet
.
user_id_str
,
"username"
:
Tweet
.
username
,
"username"
:
Tweet
.
username
,
"name"
:
Tweet
.
name
,
"name"
:
Tweet
.
name
,
"day"
:
da
y
,
"day"
:
da
te_obj
.
weekday
()
,
"hour"
:
hour
(
Tweet
.
datetime
/
1000
)
,
"hour"
:
date_obj
.
hour
,
"link"
:
Tweet
.
link
,
"link"
:
Tweet
.
link
,
"retweet"
:
Tweet
.
retweet
,
"retweet"
:
retweet
,
"essid"
:
config
.
Essid
,
"essid"
:
config
.
Essid
,
"nlikes"
:
int
(
Tweet
.
likes_count
),
"nlikes"
:
int
(
Tweet
.
likes_count
),
"nreplies"
:
int
(
Tweet
.
replies_count
),
"nreplies"
:
int
(
Tweet
.
replies_count
),
...
@@ -245,7 +238,7 @@ def Tweet(Tweet, config):
...
@@ -245,7 +238,7 @@ def Tweet(Tweet, config):
"near"
:
config
.
Near
"near"
:
config
.
Near
}
}
}
}
if
Tweet
.
retweet
:
if
retweet
is
not
None
:
j_data
[
"_source"
]
.
update
({
"user_rt_id"
:
Tweet
.
user_rt_id
})
j_data
[
"_source"
]
.
update
({
"user_rt_id"
:
Tweet
.
user_rt_id
})
j_data
[
"_source"
]
.
update
({
"user_rt"
:
Tweet
.
user_rt
})
j_data
[
"_source"
]
.
update
({
"user_rt"
:
Tweet
.
user_rt
})
j_data
[
"_source"
]
.
update
({
"retweet_id"
:
Tweet
.
retweet_id
})
j_data
[
"_source"
]
.
update
({
"retweet_id"
:
Tweet
.
retweet_id
})
...
...
twint/storage/panda.py
View file @
2348211b
import
datetime
,
pandas
as
pd
,
warnings
import
datetime
,
pandas
as
pd
,
warnings
from
time
import
strftime
,
localtime
from
time
import
strftime
,
localtime
from
.elasticsearch
import
hour
from
twint.tweet
import
Tweet_formats
from
twint.tweet
import
Tweet_formats
Tweets_df
=
None
Tweets_df
=
None
...
@@ -85,7 +84,7 @@ def update(object, config):
...
@@ -85,7 +84,7 @@ def update(object, config):
"username"
:
Tweet
.
username
,
"username"
:
Tweet
.
username
,
"name"
:
Tweet
.
name
,
"name"
:
Tweet
.
name
,
"day"
:
day
,
"day"
:
day
,
"hour"
:
hour
(
datetime_ms
/
1000
),
"hour"
:
datetime
.
strptime
(
"
%
H"
,
localtime
(
datetime_ms
/
1000
)
),
"link"
:
Tweet
.
link
,
"link"
:
Tweet
.
link
,
"urls"
:
Tweet
.
urls
,
"urls"
:
Tweet
.
urls
,
"photos"
:
Tweet
.
photos
,
"photos"
:
Tweet
.
photos
,
...
...
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