Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
S
SACHA txt Downloader
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
Package registry
Model registry
Operate
Environments
Terraform modules
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
skurzinz
SACHA txt Downloader
Commits
a6a499ef
Commit
a6a499ef
authored
4 years ago
by
Georg Petz
Browse files
Options
Downloads
Patches
Plain Diff
update
parent
361264ae
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
txtDownloader.ipynb
+70
-27
70 additions, 27 deletions
txtDownloader.ipynb
with
70 additions
and
27 deletions
txtDownloader.ipynb
+
70
−
27
View file @
a6a499ef
...
@@ -2,7 +2,7 @@
...
@@ -2,7 +2,7 @@
"cells": [
"cells": [
{
{
"cell_type": "code",
"cell_type": "code",
"execution_count":
4
,
"execution_count":
1
,
"metadata": {},
"metadata": {},
"outputs": [],
"outputs": [],
"source": [
"source": [
...
@@ -10,40 +10,76 @@
...
@@ -10,40 +10,76 @@
"from zipfile import ZipFile"
"from zipfile import ZipFile"
]
]
},
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"e.g.:+Z196807705"
]
},
{
{
"cell_type": "code",
"cell_type": "code",
"execution_count":
5
,
"execution_count":
2
,
"metadata": {},
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"+Z196807705\n"
]
}
],
"source": [
"source": [
"
url=\"https://iiif.onb.ac.at/presentation/ABO/+Z196807705/manifest/\"
"
"
barcode=input()
"
]
]
},
},
{
{
"cell_type": "code",
"cell_type": "code",
"execution_count": 6,
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'https://iiif.onb.ac.at/presentation/ABO/+Z196807705/manifest/'"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"url=\"https://iiif.onb.ac.at/presentation/ABO/\"+barcode+\"/manifest/\"\n",
"url"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"metadata": {},
"outputs": [
"outputs": [
{
{
"name": "stdout",
"name": "stdout",
"output_type": "stream",
"output_type": "stream",
"text": [
"text": [
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000001.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000001.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000002.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000002.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000003.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000003.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000004.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000004.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000005.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000005.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000006.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000006.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000007.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000007.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000008.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000008.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000009.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000009.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000010.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000010.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000011.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000011.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000012.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000012.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000013.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000013.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000014.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000014.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000015.txt\n",
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000015.txt\n",
"https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000016.txt\n"
"
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000016.txt\n"
]
]
}
}
],
],
...
@@ -52,17 +88,24 @@
...
@@ -52,17 +88,24 @@
"data = json.loads(response.read())\n",
"data = json.loads(response.read())\n",
"\n",
"\n",
"i=0\n",
"i=0\n",
"zipObj = ZipFile('downloadTXT.zip', 'w')\n",
"zipObj = ZipFile(barcode + \".zip\", \"w\")\n",
"all_txt = open(\"all.txt\",\"wb\")\n",
"\n",
"\n",
"for page in data[\"sequences\"][0][\"canvases\"]:\n",
"for page in data[\"sequences\"][0][\"canvases\"]:\n",
" txt_url = page[\"otherContent\"][0][\"resources\"][0][\"resource\"][\"@id\"]\n",
" txt_url = page[\"otherContent\"][0][\"resources\"][0][\"resource\"][\"@id\"]\n",
" i=i+1\n",
" i=i+1\n",
" print(txt_url)\n",
" print(
\"downloading \" +
txt_url)\n",
" output_file = str(i) + \".txt\"\n",
" output_file = str(i) + \".txt\"\n",
" with urllib.request.urlopen(txt_url) as response, open(output_file,
'wb'
) as out_file:\n",
" with urllib.request.urlopen(txt_url) as response, open(output_file,
\"wb\"
) as out_file:\n",
" shutil.copyfileobj(response, out_file)\n",
" shutil.copyfileobj(response, out_file)\n",
" zipObj.write(os.path.abspath(output_file))\n",
" zipObj.write(os.path.abspath(output_file),output_file)\n",
" \n",
" txt_page = open(output_file, \"rb\")\n",
" shutil.copyfileobj(txt_page, all_txt)\n",
" txt_page.close\n",
" os.remove(output_file)\n",
"zipObj.write(\"all.txt\")\n",
"all_txt.close()\n",
"os.remove(\"all.txt\")\n",
"zipObj.close()"
"zipObj.close()"
]
]
},
},
...
...
%% Cell type:code id: tags:
%% Cell type:code id: tags:
```
python
```
python
import
urllib.request
,
json
,
shutil
,
os
import
urllib.request
,
json
,
shutil
,
os
from
zipfile
import
ZipFile
from
zipfile
import
ZipFile
```
```
%% Cell type:markdown id: tags:
e.g.:+Z196807705
%% Cell type:code id: tags:
```
python
barcode
=
input
()
```
%% Output
+Z196807705
%% Cell type:code id: tags:
%% Cell type:code id: tags:
```
python
```
python
url
=
"
https://iiif.onb.ac.at/presentation/ABO/+Z196807705/manifest/
"
url
=
"
https://iiif.onb.ac.at/presentation/ABO/
"
+
barcode
+
"
/manifest/
"
url
```
```
%% Output
'https://iiif.onb.ac.at/presentation/ABO/+Z196807705/manifest/'
%% Cell type:code id: tags:
%% Cell type:code id: tags:
```
python
```
python
response
=
urllib
.
request
.
urlopen
(
url
)
response
=
urllib
.
request
.
urlopen
(
url
)
data
=
json
.
loads
(
response
.
read
())
data
=
json
.
loads
(
response
.
read
())
i
=
0
i
=
0
zipObj
=
ZipFile
(
'
downloadTXT.zip
'
,
'
w
'
)
zipObj
=
ZipFile
(
barcode
+
"
.zip
"
,
"
w
"
)
all_txt
=
open
(
"
all.txt
"
,
"
wb
"
)
for
page
in
data
[
"
sequences
"
][
0
][
"
canvases
"
]:
for
page
in
data
[
"
sequences
"
][
0
][
"
canvases
"
]:
txt_url
=
page
[
"
otherContent
"
][
0
][
"
resources
"
][
0
][
"
resource
"
][
"
@id
"
]
txt_url
=
page
[
"
otherContent
"
][
0
][
"
resources
"
][
0
][
"
resource
"
][
"
@id
"
]
i
=
i
+
1
i
=
i
+
1
print
(
txt_url
)
print
(
"
downloading
"
+
txt_url
)
output_file
=
str
(
i
)
+
"
.txt
"
output_file
=
str
(
i
)
+
"
.txt
"
with
urllib
.
request
.
urlopen
(
txt_url
)
as
response
,
open
(
output_file
,
'
wb
'
)
as
out_file
:
with
urllib
.
request
.
urlopen
(
txt_url
)
as
response
,
open
(
output_file
,
"
wb
"
)
as
out_file
:
shutil
.
copyfileobj
(
response
,
out_file
)
shutil
.
copyfileobj
(
response
,
out_file
)
zipObj
.
write
(
os
.
path
.
abspath
(
output_file
))
zipObj
.
write
(
os
.
path
.
abspath
(
output_file
),
output_file
)
txt_page
=
open
(
output_file
,
"
rb
"
)
shutil
.
copyfileobj
(
txt_page
,
all_txt
)
txt_page
.
close
os
.
remove
(
output_file
)
zipObj
.
write
(
"
all.txt
"
)
all_txt
.
close
()
os
.
remove
(
"
all.txt
"
)
zipObj
.
close
()
zipObj
.
close
()
```
```
%% Output
%% Output
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000001.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000001.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000002.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000002.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000003.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000003.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000004.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000004.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000005.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000005.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000006.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000006.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000007.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000007.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000008.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000008.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000009.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000009.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000010.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000010.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000011.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000011.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000012.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000012.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000013.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000013.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000014.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000014.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000015.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000015.txt
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000016.txt
downloading
https://iiif.onb.ac.at/presentation/ABO/Z196807705/resource/00000016.txt
%% Cell type:code id: tags:
%% Cell type:code id: tags:
```
python
```
python
```
```
...
...
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