Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
W
webarchive-api
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
aponb
webarchive-api
Commits
60c8c0ff
Commit
60c8c0ff
authored
6 years ago
by
Stefan Karner
Browse files
Options
Downloads
Patches
Plain Diff
Refactor method names
parent
8dc2b37d
Branches
Branches containing commit
No related tags found
No related merge requests found
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
webarchiv.py
+17
-16
17 additions, 16 deletions
webarchiv.py
with
17 additions
and
16 deletions
webarchiv.py
+
17
−
16
View file @
60c8c0ff
...
...
@@ -108,7 +108,8 @@ class WebarchivSession:
response_text
=
e
.
response
.
text
),
file
=
sys
.
stderr
)
def
_handle_response_errors
(
self
,
r
):
@staticmethod
def
_handle_response_errors
(
r
):
if
r
.
status_code
==
403
:
print
(
'
Forbidden. Invalid Token or ApiKey transmitted
'
,
file
=
sys
.
stderr
)
return
r
...
...
@@ -166,7 +167,7 @@ class WebarchivSession:
try
:
response
=
self
.
_get
(
op
=
'
/search/fulltext
'
,
params
=
params
)
return
self
.
wait
ForR
esponse
(
response
)
return
self
.
wait
_for_r
esponse
(
response
)
except
HTTPError
as
e
:
self
.
_display_http_error
(
e
)
...
...
@@ -192,7 +193,7 @@ class WebarchivSession:
try
:
response
=
self
.
_get
(
op
=
'
/search/fulltext/seed
'
,
params
=
params
)
return
self
.
wait
ForR
esponse
(
response
)
return
self
.
wait
_for_r
esponse
(
response
)
except
HTTPError
as
e
:
self
.
_display_http_error
(
e
)
...
...
@@ -217,7 +218,7 @@ class WebarchivSession:
try
:
response
=
self
.
_get
(
op
=
'
/search/fulltext/capture
'
,
params
=
params
)
return
self
.
wait
ForR
esponse
(
response
)
return
self
.
wait
_for_r
esponse
(
response
)
except
HTTPError
as
e
:
self
.
_display_http_error
(
e
)
...
...
@@ -241,13 +242,13 @@ class WebarchivSession:
try
:
response
=
self
.
_get
(
op
=
'
/search/wayback
'
,
params
=
params
)
return
self
.
wait
ForR
esponse
(
response
)
return
self
.
wait
_for_r
esponse
(
response
)
except
HTTPError
as
e
:
self
.
_display_http_error
(
e
)
print
(
'
Error:
'
.
format
(
query_string
))
def
wait
ForR
esponse
(
self
,
response
):
def
wait
_for_r
esponse
(
self
,
response
):
"""
Polls until the server responds with a result
"""
...
...
@@ -296,7 +297,7 @@ class WebarchivSession:
try
:
response
=
self
.
_get
(
op
=
'
/search/domainname
'
,
params
=
params
)
return
self
.
wait
ForR
esponse
(
response
)
return
self
.
wait
_for_r
esponse
(
response
)
except
HTTPError
as
e
:
self
.
_display_http_error
(
e
)
...
...
@@ -319,30 +320,30 @@ class WebarchivSession:
try
:
response
=
self
.
_get
(
op
=
'
/search/fulltext/histogram
'
,
params
=
params
)
return
self
.
wait
ForR
esponse
(
response
)
return
self
.
wait
_for_r
esponse
(
response
)
except
HTTPError
as
e
:
self
.
_display_http_error
(
e
)
print
(
'
Error:
'
.
format
(
query_string
))
def
get
S
napshot
U
rl
(
self
,
seed
,
capture
,
onlysvg
):
def
get
_s
napshot
_u
rl
(
self
,
seed
,
capture
,
onlysvg
):
return
self
.
api_path
+
'
snapshot?capture=
'
+
capture
+
'
&t=
'
+
self
.
token
+
'
&apikey=
'
+
self
.
api_key
+
'
&onlysvg=
'
+
onlysvg
+
'
&seed=
'
+
seed
@staticmethod
def
result
C
ontains
S
eeds
(
response
):
def
result
_c
ontains
_s
eeds
(
response
):
try
:
return
response
.
json
()[
'
subtype
'
]
==
2
except
:
return
False
@staticmethod
def
result
C
ontains
C
aptures
(
response
):
def
result
_c
ontains
_c
aptures
(
response
):
try
:
return
response
.
json
()[
'
subtype
'
]
==
3
except
:
return
False
def
save
P
age
(
self
,
url
):
def
save
_p
age
(
self
,
url
):
self
.
connect
()
r
=
requests
.
post
(
self
.
base_url
.
format
(
'
savepage
'
),
data
=
'''
{{
...
...
@@ -357,7 +358,7 @@ class WebarchivSession:
)
return
r
def
fragment
C
hecksum
H
tml
(
self
,
seed
,
capture
,
selector
,
occurrence
):
def
fragment
_c
hecksum
_h
tml
(
self
,
seed
,
capture
,
selector
,
occurrence
):
try
:
response
=
self
.
_post
(
op
=
'
/fragment/checksum/html
'
,
json
=
{
"
seed
"
:
seed
,
...
...
@@ -367,7 +368,7 @@ class WebarchivSession:
"
extractortype
"
:
EXTRACTOR_HTML
})
response
=
self
.
status_query
(
response
)
return
self
.
wait
ForR
esponse
(
response
)
return
self
.
wait
_for_r
esponse
(
response
)
except
HTTPError
as
e
:
self
.
_display_http_error
(
e
)
...
...
@@ -393,7 +394,7 @@ if __name__ == '__main__':
for
capture
in
response
.
json
()[
'
hits
'
]:
capturedate
=
capture
[
'
c
'
]
resp
=
w
.
fragment
C
hecksum
H
tml
(
url
,
capturedate
,
"
.odd td
"
,
3
)
resp
=
w
.
fragment
_c
hecksum
_h
tml
(
url
,
capturedate
,
"
.odd td
"
,
3
)
checksum
=
resp
.
json
()[
'
checksum
'
]
returncode
=
resp
.
json
()[
'
returncode
'
]
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment