pywaybackup 1.2.4__tar.gz → 1.2.6__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- pywaybackup-1.2.6/.github/ISSUE_TEMPLATE/bug.md +25 -0
- pywaybackup-1.2.6/.gitignore +164 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/PKG-INFO +3 -2
- pywaybackup-1.2.6/dev/pip_build.sh +16 -0
- pywaybackup-1.2.6/dev/venv_create.sh +17 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup/Verbosity.py +1 -1
- pywaybackup-1.2.6/pywaybackup/__version__.py +1 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup/archive.py +3 -3
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup.egg-info/PKG-INFO +3 -2
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup.egg-info/SOURCES.txt +9 -1
- pywaybackup-1.2.6/pywaybackup.egg-info/requires.txt +8 -0
- pywaybackup-1.2.6/requirements.txt +4 -0
- pywaybackup-1.2.6/test/cdx.example.com.200 +2851 -0
- pywaybackup-1.2.6/test/cdx.example.com.404 +9163 -0
- pywaybackup-1.2.6/test/cdx.example.com.small.200 +46 -0
- pywaybackup-1.2.4/pywaybackup/__version__.py +0 -1
- pywaybackup-1.2.4/pywaybackup.egg-info/requires.txt +0 -3
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/LICENSE +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/README.md +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup/Exception.py +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup/SnapshotCollection.py +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup/__init__.py +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup/arguments.py +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup/helper.py +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup/main.py +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup.egg-info/dependency_links.txt +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup.egg-info/entry_points.txt +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/pywaybackup.egg-info/top_level.txt +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/setup.cfg +0 -0
- {pywaybackup-1.2.4 → pywaybackup-1.2.6}/setup.py +0 -0
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: Bug
|
|
3
|
+
about: Describe a faulty behavior
|
|
4
|
+
title: ''
|
|
5
|
+
labels: bug
|
|
6
|
+
assignees: ''
|
|
7
|
+
|
|
8
|
+
---
|
|
9
|
+
|
|
10
|
+
**Describe**
|
|
11
|
+
Describe the bug / unexpected event
|
|
12
|
+
|
|
13
|
+
**Snapshot to reproduce**
|
|
14
|
+
<a href="https://example.com">If possible add a link to the snapshot which caused the error.</a>
|
|
15
|
+
|
|
16
|
+
**Command to reproduce**
|
|
17
|
+
`Add the used command`
|
|
18
|
+
|
|
19
|
+
**Terminal output**
|
|
20
|
+
```
|
|
21
|
+
Insert exception / output if possible - remove private folders / files
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
**Additional context**
|
|
25
|
+
Add any other context about the problem here.
|
|
@@ -0,0 +1,164 @@
|
|
|
1
|
+
waybackup_snapshots/
|
|
2
|
+
|
|
3
|
+
# Byte-compiled / optimized / DLL files
|
|
4
|
+
__pycache__/
|
|
5
|
+
*.py[cod]
|
|
6
|
+
*$py.class
|
|
7
|
+
|
|
8
|
+
# C extensions
|
|
9
|
+
*.so
|
|
10
|
+
|
|
11
|
+
# Distribution / packaging
|
|
12
|
+
.Python
|
|
13
|
+
build/
|
|
14
|
+
develop-eggs/
|
|
15
|
+
dist/
|
|
16
|
+
downloads/
|
|
17
|
+
eggs/
|
|
18
|
+
.eggs/
|
|
19
|
+
lib/
|
|
20
|
+
lib64/
|
|
21
|
+
parts/
|
|
22
|
+
sdist/
|
|
23
|
+
var/
|
|
24
|
+
wheels/
|
|
25
|
+
share/python-wheels/
|
|
26
|
+
*.egg-info/
|
|
27
|
+
.installed.cfg
|
|
28
|
+
*.egg
|
|
29
|
+
MANIFEST
|
|
30
|
+
|
|
31
|
+
# PyInstaller
|
|
32
|
+
# Usually these files are written by a python script from a template
|
|
33
|
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
|
34
|
+
*.manifest
|
|
35
|
+
*.spec
|
|
36
|
+
|
|
37
|
+
# Installer logs
|
|
38
|
+
pip-log.txt
|
|
39
|
+
pip-delete-this-directory.txt
|
|
40
|
+
|
|
41
|
+
# Unit test / coverage reports
|
|
42
|
+
htmlcov/
|
|
43
|
+
.tox/
|
|
44
|
+
.nox/
|
|
45
|
+
.coverage
|
|
46
|
+
.coverage.*
|
|
47
|
+
.cache
|
|
48
|
+
nosetests.xml
|
|
49
|
+
coverage.xml
|
|
50
|
+
*.cover
|
|
51
|
+
*.py,cover
|
|
52
|
+
.hypothesis/
|
|
53
|
+
.pytest_cache/
|
|
54
|
+
cover/
|
|
55
|
+
|
|
56
|
+
# Translations
|
|
57
|
+
*.mo
|
|
58
|
+
*.pot
|
|
59
|
+
|
|
60
|
+
# Django stuff:
|
|
61
|
+
*.log
|
|
62
|
+
local_settings.py
|
|
63
|
+
db.sqlite3
|
|
64
|
+
db.sqlite3-journal
|
|
65
|
+
|
|
66
|
+
# Flask stuff:
|
|
67
|
+
instance/
|
|
68
|
+
.webassets-cache
|
|
69
|
+
|
|
70
|
+
# Scrapy stuff:
|
|
71
|
+
.scrapy
|
|
72
|
+
|
|
73
|
+
# Sphinx documentation
|
|
74
|
+
docs/_build/
|
|
75
|
+
|
|
76
|
+
# PyBuilder
|
|
77
|
+
.pybuilder/
|
|
78
|
+
target/
|
|
79
|
+
|
|
80
|
+
# Jupyter Notebook
|
|
81
|
+
.ipynb_checkpoints
|
|
82
|
+
|
|
83
|
+
# IPython
|
|
84
|
+
profile_default/
|
|
85
|
+
ipython_config.py
|
|
86
|
+
|
|
87
|
+
# pyenv
|
|
88
|
+
# For a library or package, you might want to ignore these files since the code is
|
|
89
|
+
# intended to run in multiple environments; otherwise, check them in:
|
|
90
|
+
# .python-version
|
|
91
|
+
|
|
92
|
+
# pipenv
|
|
93
|
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
|
94
|
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
|
95
|
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
|
96
|
+
# install all needed dependencies.
|
|
97
|
+
#Pipfile.lock
|
|
98
|
+
|
|
99
|
+
# poetry
|
|
100
|
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
|
101
|
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
|
102
|
+
# commonly ignored for libraries.
|
|
103
|
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
|
104
|
+
#poetry.lock
|
|
105
|
+
|
|
106
|
+
# pdm
|
|
107
|
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
|
108
|
+
#pdm.lock
|
|
109
|
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
|
110
|
+
# in version control.
|
|
111
|
+
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
|
|
112
|
+
.pdm.toml
|
|
113
|
+
.pdm-python
|
|
114
|
+
.pdm-build/
|
|
115
|
+
|
|
116
|
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
|
117
|
+
__pypackages__/
|
|
118
|
+
|
|
119
|
+
# Celery stuff
|
|
120
|
+
celerybeat-schedule
|
|
121
|
+
celerybeat.pid
|
|
122
|
+
|
|
123
|
+
# SageMath parsed files
|
|
124
|
+
*.sage.py
|
|
125
|
+
|
|
126
|
+
# Environments
|
|
127
|
+
.env
|
|
128
|
+
.venv
|
|
129
|
+
env/
|
|
130
|
+
venv/
|
|
131
|
+
ENV/
|
|
132
|
+
env.bak/
|
|
133
|
+
venv.bak/
|
|
134
|
+
|
|
135
|
+
# Spyder project settings
|
|
136
|
+
.spyderproject
|
|
137
|
+
.spyproject
|
|
138
|
+
|
|
139
|
+
# Rope project settings
|
|
140
|
+
.ropeproject
|
|
141
|
+
|
|
142
|
+
# mkdocs documentation
|
|
143
|
+
/site
|
|
144
|
+
|
|
145
|
+
# mypy
|
|
146
|
+
.mypy_cache/
|
|
147
|
+
.dmypy.json
|
|
148
|
+
dmypy.json
|
|
149
|
+
|
|
150
|
+
# Pyre type checker
|
|
151
|
+
.pyre/
|
|
152
|
+
|
|
153
|
+
# pytype static type analyzer
|
|
154
|
+
.pytype/
|
|
155
|
+
|
|
156
|
+
# Cython debug symbols
|
|
157
|
+
cython_debug/
|
|
158
|
+
|
|
159
|
+
# PyCharm
|
|
160
|
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
|
161
|
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
|
162
|
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
|
163
|
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
|
164
|
+
#.idea/
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: pywaybackup
|
|
3
|
-
Version: 1.2.
|
|
3
|
+
Version: 1.2.6
|
|
4
4
|
Summary: Download snapshots from the Wayback Machine
|
|
5
5
|
Home-page: https://github.com/bitdruid/python-wayback-machine-downloader
|
|
6
6
|
Author: bitdruid
|
|
@@ -11,7 +11,8 @@ Description-Content-Type: text/markdown
|
|
|
11
11
|
License-File: LICENSE
|
|
12
12
|
Requires-Dist: requests==2.31.0
|
|
13
13
|
Requires-Dist: tqdm==4.66.2
|
|
14
|
-
Requires-Dist: python-magic==0.4.27
|
|
14
|
+
Requires-Dist: python-magic==0.4.27; sys_platform == "linux"
|
|
15
|
+
Requires-Dist: python-magic-bin==0.4.14; sys_platform == "win32"
|
|
15
16
|
|
|
16
17
|
# python wayback machine downloader
|
|
17
18
|
|
|
@@ -0,0 +1,16 @@
|
|
|
1
|
+
#!bin/bash
|
|
2
|
+
|
|
3
|
+
# path of the script
|
|
4
|
+
SCRIPT_PATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
|
|
5
|
+
TARGET_PATH="$SCRIPT_PATH/.."
|
|
6
|
+
|
|
7
|
+
# install dependencies
|
|
8
|
+
pip install twine wheel setuptools
|
|
9
|
+
|
|
10
|
+
# build
|
|
11
|
+
python $TARGET_PATH/setup.py sdist bdist_wheel --verbose
|
|
12
|
+
python -m twine upload dist/*
|
|
13
|
+
#pip install -e $TARGET_PATH
|
|
14
|
+
|
|
15
|
+
# clean up
|
|
16
|
+
rm -rf $TARGET_PATH/build $TARGET_PATH/dist # $TARGET_PATH/*.egg-info
|
|
@@ -0,0 +1,17 @@
|
|
|
1
|
+
#!bin/bash
|
|
2
|
+
|
|
3
|
+
# path of the script
|
|
4
|
+
SCRIPT_PATH="$( cd "$( dirname "${BASH_SOURCE[0]}" )" >/dev/null 2>&1 && pwd )"
|
|
5
|
+
TARGET_PATH="$SCRIPT_PATH/.."
|
|
6
|
+
echo "Preparing virtual environment in $TARGET_PATH"
|
|
7
|
+
# Create a virtual environment
|
|
8
|
+
if [ ! -d "..$SCRIPT_PATH/.venv" ]; then
|
|
9
|
+
python3 -m venv "$TARGET_PATH/.venv"
|
|
10
|
+
fi
|
|
11
|
+
|
|
12
|
+
# update pip
|
|
13
|
+
"$TARGET_PATH/.venv/bin/python" -m pip install --upgrade pip
|
|
14
|
+
"$TARGET_PATH/.venv/bin/python" -m pip install twine wheel setuptools
|
|
15
|
+
|
|
16
|
+
# install requirements
|
|
17
|
+
"$TARGET_PATH/.venv/bin/python" -m pip install -r "$TARGET_PATH/requirements.txt"
|
|
@@ -38,7 +38,7 @@ class Verbosity:
|
|
|
38
38
|
def write(cls, message: str = None, progress: int = None):
|
|
39
39
|
if cls.mode == "progress":
|
|
40
40
|
if cls.pbar is None and progress == 0:
|
|
41
|
-
maxval = sc.
|
|
41
|
+
maxval = sc.count(collection=True)
|
|
42
42
|
cls.pbar = tqdm.tqdm(total=maxval, desc="Downloading", unit=" snapshot", ascii="░▒█")
|
|
43
43
|
if cls.pbar is not None and progress is not None and progress > 0 :
|
|
44
44
|
cls.pbar.update(progress)
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
__version__ = "1.2.6"
|
|
@@ -382,15 +382,15 @@ def csv_close(csv_path: str, url: str):
|
|
|
382
382
|
if sc.count(collection=True) > 0:
|
|
383
383
|
if os.path.exists(csv_path): # append to existing file
|
|
384
384
|
existing_rows = set()
|
|
385
|
-
with open(csv_path, mode='r') as file: # read existing rows
|
|
385
|
+
with open(csv_path, mode='r', newline='') as file: # read existing rows
|
|
386
386
|
existing_rows = set(csv_read(file))
|
|
387
|
-
with open(csv_path, mode='a') as file: # append new rows
|
|
387
|
+
with open(csv_path, mode='a', newline='') as file: # append new rows
|
|
388
388
|
row = csv.DictWriter(file, sc.SNAPSHOT_COLLECTION[0].keys())
|
|
389
389
|
for snapshot in sc.SNAPSHOT_COLLECTION:
|
|
390
390
|
if snapshot["response"] is not False and snapshot["url_archive"] not in existing_rows: # only append handled snapshots
|
|
391
391
|
row.writerow(snapshot)
|
|
392
392
|
else: # create new file
|
|
393
|
-
with open(csv_path, mode='w') as file:
|
|
393
|
+
with open(csv_path, mode='w', newline='') as file:
|
|
394
394
|
row = csv.DictWriter(file, sc.SNAPSHOT_COLLECTION[0].keys())
|
|
395
395
|
row.writeheader()
|
|
396
396
|
for snapshot in sc.SNAPSHOT_COLLECTION:
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: pywaybackup
|
|
3
|
-
Version: 1.2.
|
|
3
|
+
Version: 1.2.6
|
|
4
4
|
Summary: Download snapshots from the Wayback Machine
|
|
5
5
|
Home-page: https://github.com/bitdruid/python-wayback-machine-downloader
|
|
6
6
|
Author: bitdruid
|
|
@@ -11,7 +11,8 @@ Description-Content-Type: text/markdown
|
|
|
11
11
|
License-File: LICENSE
|
|
12
12
|
Requires-Dist: requests==2.31.0
|
|
13
13
|
Requires-Dist: tqdm==4.66.2
|
|
14
|
-
Requires-Dist: python-magic==0.4.27
|
|
14
|
+
Requires-Dist: python-magic==0.4.27; sys_platform == "linux"
|
|
15
|
+
Requires-Dist: python-magic-bin==0.4.14; sys_platform == "win32"
|
|
15
16
|
|
|
16
17
|
# python wayback machine downloader
|
|
17
18
|
|
|
@@ -1,6 +1,11 @@
|
|
|
1
|
+
.gitignore
|
|
1
2
|
LICENSE
|
|
2
3
|
README.md
|
|
4
|
+
requirements.txt
|
|
3
5
|
setup.py
|
|
6
|
+
.github/ISSUE_TEMPLATE/bug.md
|
|
7
|
+
dev/pip_build.sh
|
|
8
|
+
dev/venv_create.sh
|
|
4
9
|
pywaybackup/Exception.py
|
|
5
10
|
pywaybackup/SnapshotCollection.py
|
|
6
11
|
pywaybackup/Verbosity.py
|
|
@@ -15,4 +20,7 @@ pywaybackup.egg-info/SOURCES.txt
|
|
|
15
20
|
pywaybackup.egg-info/dependency_links.txt
|
|
16
21
|
pywaybackup.egg-info/entry_points.txt
|
|
17
22
|
pywaybackup.egg-info/requires.txt
|
|
18
|
-
pywaybackup.egg-info/top_level.txt
|
|
23
|
+
pywaybackup.egg-info/top_level.txt
|
|
24
|
+
test/cdx.example.com.200
|
|
25
|
+
test/cdx.example.com.404
|
|
26
|
+
test/cdx.example.com.small.200
|