this repo has no description
twitter-to-sqlite auth and followers commands
+499
+110
.circleci/config.yml
+110
.circleci/config.yml
···
1
+
version: 2.1
2
+
workflows:
3
+
build_and_deploy:
4
+
jobs:
5
+
- build:
6
+
filters:
7
+
tags:
8
+
only: /.*/
9
+
- test-python-install:
10
+
version: "3.6"
11
+
requires:
12
+
- build
13
+
- test-python-install:
14
+
version: "3.7"
15
+
requires:
16
+
- build
17
+
- deploy:
18
+
requires:
19
+
- build
20
+
filters:
21
+
tags:
22
+
only: /[0-9]+(\.[0-9]+)*/
23
+
branches:
24
+
ignore: /.*/
25
+
jobs:
26
+
build:
27
+
docker:
28
+
- image: circleci/python:3.6
29
+
steps:
30
+
- checkout
31
+
- restore_cache:
32
+
key: v1-dependency-cache-{{ checksum "setup.py" }}
33
+
- run:
34
+
name: install python dependencies
35
+
command: |
36
+
python3 -m venv venv
37
+
. venv/bin/activate
38
+
pip install -e .
39
+
- save_cache:
40
+
key: v1-dependency-cache-{{ checksum "setup.py" }}
41
+
paths:
42
+
- "venv"
43
+
- run:
44
+
name: run tests
45
+
command: |
46
+
. venv/bin/activate
47
+
pip install -e .
48
+
pip install pytest
49
+
pytest
50
+
test-python-install:
51
+
parameters:
52
+
version:
53
+
type: string
54
+
default: latest
55
+
docker:
56
+
- image: circleci/python:3.6
57
+
steps:
58
+
- checkout
59
+
- restore_cache:
60
+
key: v1-dependency-cache-{{ checksum "setup.py" }}
61
+
- run:
62
+
name: install python dependencies
63
+
command: |
64
+
python3 -m venv venv
65
+
. venv/bin/activate
66
+
pip install -e .
67
+
- save_cache:
68
+
key: v1-dependency-cache-{{ checksum "setup.py" }}
69
+
paths:
70
+
- "venv"
71
+
- run:
72
+
name: run tests
73
+
command: |
74
+
. venv/bin/activate
75
+
pip install -e .
76
+
pip install pytest
77
+
pytest
78
+
deploy:
79
+
docker:
80
+
- image: circleci/python:3.6
81
+
steps:
82
+
- checkout
83
+
- restore_cache:
84
+
key: v1-dependency-cache-{{ checksum "setup.py" }}
85
+
- run:
86
+
name: install python dependencies
87
+
command: |
88
+
python3 -m venv venv
89
+
. venv/bin/activate
90
+
pip install -e .
91
+
- save_cache:
92
+
key: v1-dependency-cache-{{ checksum "setup.py" }}
93
+
paths:
94
+
- "venv"
95
+
- run:
96
+
name: init .pypirc
97
+
command: |
98
+
echo -e "[pypi]" >> ~/.pypirc
99
+
echo -e "username = simonw" >> ~/.pypirc
100
+
echo -e "password = $PYPI_PASSWORD" >> ~/.pypirc
101
+
- run:
102
+
name: create packages
103
+
command: |
104
+
python setup.py bdist_wheel
105
+
- run:
106
+
name: upload to pypi
107
+
command: |
108
+
. venv/bin/activate
109
+
pip install twine
110
+
twine upload dist/*
+8
.gitignore
+8
.gitignore
+201
LICENSE
+201
LICENSE
···
1
+
Apache License
2
+
Version 2.0, January 2004
3
+
http://www.apache.org/licenses/
4
+
5
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6
+
7
+
1. Definitions.
8
+
9
+
"License" shall mean the terms and conditions for use, reproduction,
10
+
and distribution as defined by Sections 1 through 9 of this document.
11
+
12
+
"Licensor" shall mean the copyright owner or entity authorized by
13
+
the copyright owner that is granting the License.
14
+
15
+
"Legal Entity" shall mean the union of the acting entity and all
16
+
other entities that control, are controlled by, or are under common
17
+
control with that entity. For the purposes of this definition,
18
+
"control" means (i) the power, direct or indirect, to cause the
19
+
direction or management of such entity, whether by contract or
20
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
21
+
outstanding shares, or (iii) beneficial ownership of such entity.
22
+
23
+
"You" (or "Your") shall mean an individual or Legal Entity
24
+
exercising permissions granted by this License.
25
+
26
+
"Source" form shall mean the preferred form for making modifications,
27
+
including but not limited to software source code, documentation
28
+
source, and configuration files.
29
+
30
+
"Object" form shall mean any form resulting from mechanical
31
+
transformation or translation of a Source form, including but
32
+
not limited to compiled object code, generated documentation,
33
+
and conversions to other media types.
34
+
35
+
"Work" shall mean the work of authorship, whether in Source or
36
+
Object form, made available under the License, as indicated by a
37
+
copyright notice that is included in or attached to the work
38
+
(an example is provided in the Appendix below).
39
+
40
+
"Derivative Works" shall mean any work, whether in Source or Object
41
+
form, that is based on (or derived from) the Work and for which the
42
+
editorial revisions, annotations, elaborations, or other modifications
43
+
represent, as a whole, an original work of authorship. For the purposes
44
+
of this License, Derivative Works shall not include works that remain
45
+
separable from, or merely link (or bind by name) to the interfaces of,
46
+
the Work and Derivative Works thereof.
47
+
48
+
"Contribution" shall mean any work of authorship, including
49
+
the original version of the Work and any modifications or additions
50
+
to that Work or Derivative Works thereof, that is intentionally
51
+
submitted to Licensor for inclusion in the Work by the copyright owner
52
+
or by an individual or Legal Entity authorized to submit on behalf of
53
+
the copyright owner. For the purposes of this definition, "submitted"
54
+
means any form of electronic, verbal, or written communication sent
55
+
to the Licensor or its representatives, including but not limited to
56
+
communication on electronic mailing lists, source code control systems,
57
+
and issue tracking systems that are managed by, or on behalf of, the
58
+
Licensor for the purpose of discussing and improving the Work, but
59
+
excluding communication that is conspicuously marked or otherwise
60
+
designated in writing by the copyright owner as "Not a Contribution."
61
+
62
+
"Contributor" shall mean Licensor and any individual or Legal Entity
63
+
on behalf of whom a Contribution has been received by Licensor and
64
+
subsequently incorporated within the Work.
65
+
66
+
2. Grant of Copyright License. Subject to the terms and conditions of
67
+
this License, each Contributor hereby grants to You a perpetual,
68
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69
+
copyright license to reproduce, prepare Derivative Works of,
70
+
publicly display, publicly perform, sublicense, and distribute the
71
+
Work and such Derivative Works in Source or Object form.
72
+
73
+
3. Grant of Patent License. Subject to the terms and conditions of
74
+
this License, each Contributor hereby grants to You a perpetual,
75
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76
+
(except as stated in this section) patent license to make, have made,
77
+
use, offer to sell, sell, import, and otherwise transfer the Work,
78
+
where such license applies only to those patent claims licensable
79
+
by such Contributor that are necessarily infringed by their
80
+
Contribution(s) alone or by combination of their Contribution(s)
81
+
with the Work to which such Contribution(s) was submitted. If You
82
+
institute patent litigation against any entity (including a
83
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
84
+
or a Contribution incorporated within the Work constitutes direct
85
+
or contributory patent infringement, then any patent licenses
86
+
granted to You under this License for that Work shall terminate
87
+
as of the date such litigation is filed.
88
+
89
+
4. Redistribution. You may reproduce and distribute copies of the
90
+
Work or Derivative Works thereof in any medium, with or without
91
+
modifications, and in Source or Object form, provided that You
92
+
meet the following conditions:
93
+
94
+
(a) You must give any other recipients of the Work or
95
+
Derivative Works a copy of this License; and
96
+
97
+
(b) You must cause any modified files to carry prominent notices
98
+
stating that You changed the files; and
99
+
100
+
(c) You must retain, in the Source form of any Derivative Works
101
+
that You distribute, all copyright, patent, trademark, and
102
+
attribution notices from the Source form of the Work,
103
+
excluding those notices that do not pertain to any part of
104
+
the Derivative Works; and
105
+
106
+
(d) If the Work includes a "NOTICE" text file as part of its
107
+
distribution, then any Derivative Works that You distribute must
108
+
include a readable copy of the attribution notices contained
109
+
within such NOTICE file, excluding those notices that do not
110
+
pertain to any part of the Derivative Works, in at least one
111
+
of the following places: within a NOTICE text file distributed
112
+
as part of the Derivative Works; within the Source form or
113
+
documentation, if provided along with the Derivative Works; or,
114
+
within a display generated by the Derivative Works, if and
115
+
wherever such third-party notices normally appear. The contents
116
+
of the NOTICE file are for informational purposes only and
117
+
do not modify the License. You may add Your own attribution
118
+
notices within Derivative Works that You distribute, alongside
119
+
or as an addendum to the NOTICE text from the Work, provided
120
+
that such additional attribution notices cannot be construed
121
+
as modifying the License.
122
+
123
+
You may add Your own copyright statement to Your modifications and
124
+
may provide additional or different license terms and conditions
125
+
for use, reproduction, or distribution of Your modifications, or
126
+
for any such Derivative Works as a whole, provided Your use,
127
+
reproduction, and distribution of the Work otherwise complies with
128
+
the conditions stated in this License.
129
+
130
+
5. Submission of Contributions. Unless You explicitly state otherwise,
131
+
any Contribution intentionally submitted for inclusion in the Work
132
+
by You to the Licensor shall be under the terms and conditions of
133
+
this License, without any additional terms or conditions.
134
+
Notwithstanding the above, nothing herein shall supersede or modify
135
+
the terms of any separate license agreement you may have executed
136
+
with Licensor regarding such Contributions.
137
+
138
+
6. Trademarks. This License does not grant permission to use the trade
139
+
names, trademarks, service marks, or product names of the Licensor,
140
+
except as required for reasonable and customary use in describing the
141
+
origin of the Work and reproducing the content of the NOTICE file.
142
+
143
+
7. Disclaimer of Warranty. Unless required by applicable law or
144
+
agreed to in writing, Licensor provides the Work (and each
145
+
Contributor provides its Contributions) on an "AS IS" BASIS,
146
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147
+
implied, including, without limitation, any warranties or conditions
148
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149
+
PARTICULAR PURPOSE. You are solely responsible for determining the
150
+
appropriateness of using or redistributing the Work and assume any
151
+
risks associated with Your exercise of permissions under this License.
152
+
153
+
8. Limitation of Liability. In no event and under no legal theory,
154
+
whether in tort (including negligence), contract, or otherwise,
155
+
unless required by applicable law (such as deliberate and grossly
156
+
negligent acts) or agreed to in writing, shall any Contributor be
157
+
liable to You for damages, including any direct, indirect, special,
158
+
incidental, or consequential damages of any character arising as a
159
+
result of this License or out of the use or inability to use the
160
+
Work (including but not limited to damages for loss of goodwill,
161
+
work stoppage, computer failure or malfunction, or any and all
162
+
other commercial damages or losses), even if such Contributor
163
+
has been advised of the possibility of such damages.
164
+
165
+
9. Accepting Warranty or Additional Liability. While redistributing
166
+
the Work or Derivative Works thereof, You may choose to offer,
167
+
and charge a fee for, acceptance of support, warranty, indemnity,
168
+
or other liability obligations and/or rights consistent with this
169
+
License. However, in accepting such obligations, You may act only
170
+
on Your own behalf and on Your sole responsibility, not on behalf
171
+
of any other Contributor, and only if You agree to indemnify,
172
+
defend, and hold each Contributor harmless for any liability
173
+
incurred by, or claims asserted against, such Contributor by reason
174
+
of your accepting any such warranty or additional liability.
175
+
176
+
END OF TERMS AND CONDITIONS
177
+
178
+
APPENDIX: How to apply the Apache License to your work.
179
+
180
+
To apply the Apache License to your work, attach the following
181
+
boilerplate notice, with the fields enclosed by brackets "[]"
182
+
replaced with your own identifying information. (Don't include
183
+
the brackets!) The text should be enclosed in the appropriate
184
+
comment syntax for the file format. We also recommend that a
185
+
file or class name and description of purpose be included on the
186
+
same "printed page" as the copyright notice for easier
187
+
identification within third-party archives.
188
+
189
+
Copyright [yyyy] [name of copyright owner]
190
+
191
+
Licensed under the Apache License, Version 2.0 (the "License");
192
+
you may not use this file except in compliance with the License.
193
+
You may obtain a copy of the License at
194
+
195
+
http://www.apache.org/licenses/LICENSE-2.0
196
+
197
+
Unless required by applicable law or agreed to in writing, software
198
+
distributed under the License is distributed on an "AS IS" BASIS,
199
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200
+
See the License for the specific language governing permissions and
201
+
limitations under the License.
+11
README.md
+11
README.md
···
1
+
# twitter-to-sqlite
2
+
3
+
[](https://pypi.org/project/twitter-to-sqlite/)
4
+
[](https://circleci.com/gh/dogsheep/twitter-to-sqlite)
5
+
[](https://github.com/dogsheep/twitter-to-sqlite/blob/master/LICENSE)
6
+
7
+
Save data from Twitter to a SQLite database.
8
+
9
+
## How to install
10
+
11
+
$ pip install twitter-to-sqlite
+32
setup.py
+32
setup.py
···
1
+
from setuptools import setup
2
+
import os
3
+
4
+
VERSION = "0.3"
5
+
6
+
7
+
def get_long_description():
8
+
with open(
9
+
os.path.join(os.path.dirname(os.path.abspath(__file__)), "README.md"),
10
+
encoding="utf8",
11
+
) as fp:
12
+
return fp.read()
13
+
14
+
15
+
setup(
16
+
name="twitter-to-sqlite",
17
+
description="Save data from Twitter to a SQLite database",
18
+
long_description=get_long_description(),
19
+
long_description_content_type="text/markdown",
20
+
author="Simon Willison",
21
+
url="https://github.com/dogsheep/twitter-to-sqlite",
22
+
license="Apache License, Version 2.0",
23
+
version=VERSION,
24
+
packages=["twitter_to_sqlite"],
25
+
entry_points="""
26
+
[console_scripts]
27
+
twitter-to-sqlite=twitter_to_sqlite.cli:cli
28
+
""",
29
+
install_requires=["sqlite-utils~=1.11", "requests-oauthlib~=1.2.0"],
30
+
extras_require={"test": ["pytest"]},
31
+
tests_require=["twitter-to-sqlite[test]"],
32
+
)
twitter_to_sqlite/__init__.py
twitter_to_sqlite/__init__.py
This is a binary file and will not be displayed.
+86
twitter_to_sqlite/cli.py
+86
twitter_to_sqlite/cli.py
···
1
+
import click
2
+
import os
3
+
import sqlite_utils
4
+
import json
5
+
from twitter_to_sqlite import utils
6
+
7
+
8
+
@click.group()
9
+
@click.version_option()
10
+
def cli():
11
+
"Save data from Twitter to a SQLite database"
12
+
13
+
14
+
@cli.command()
15
+
@click.argument(
16
+
"auth_path",
17
+
type=click.Path(file_okay=True, dir_okay=False, allow_dash=False),
18
+
default="auth.json",
19
+
)
20
+
def auth(auth_path):
21
+
"Save authentication credentials to a JSON file"
22
+
click.echo("Create an app here: https://developer.twitter.com/en/apps")
23
+
click.echo("Then navigate to 'Keys and tokens' and paste in the following:")
24
+
click.echo()
25
+
api_key = click.prompt("API key")
26
+
api_secret_key = click.prompt("API secret key")
27
+
access_token = click.prompt("Access token")
28
+
access_token_secret = click.prompt("Access token secret")
29
+
open(auth_path, "w").write(
30
+
json.dumps(
31
+
{
32
+
"api_key": api_key,
33
+
"api_secret_key": api_secret_key,
34
+
"access_token": access_token,
35
+
"access_token_secret": access_token_secret,
36
+
},
37
+
indent=4,
38
+
)
39
+
+ "\n"
40
+
)
41
+
42
+
43
+
@cli.command()
44
+
@click.argument(
45
+
"db_path",
46
+
type=click.Path(file_okay=True, dir_okay=False, allow_dash=False),
47
+
required=True,
48
+
)
49
+
@click.argument(
50
+
"auth_path",
51
+
type=click.Path(file_okay=True, dir_okay=False, allow_dash=True, exists=True),
52
+
default="auth.json",
53
+
)
54
+
@click.option("--user_id", help="Numeric user ID")
55
+
@click.option("--screen_name", help="Screen name")
56
+
@click.option("--silent", is_flag=True, help="Disable progress bar")
57
+
def followers(db_path, auth_path, user_id, screen_name, silent):
58
+
"Save followers for specified user (defaults to authenticated user)"
59
+
auth = json.load(open(auth_path))
60
+
session = utils.session_for_auth(auth)
61
+
db = sqlite_utils.Database(db_path)
62
+
fetched = []
63
+
# Get the follower count, so we can have a progress bar
64
+
count = 0
65
+
66
+
def go(update):
67
+
for followers_chunk in utils.fetch_follower_chunks(
68
+
session, user_id, screen_name
69
+
):
70
+
fetched.extend(followers_chunk)
71
+
with db.conn:
72
+
db["followers"].upsert_all(followers_chunk)
73
+
update(len(followers_chunk))
74
+
75
+
if not silent:
76
+
profile = utils.get_profile(session, user_id, screen_name)
77
+
screen_name = profile["screen_name"]
78
+
count = profile["followers_count"]
79
+
with click.progressbar(
80
+
length=count,
81
+
label="Importing {:,} followers for @{}".format(count, screen_name),
82
+
) as bar:
83
+
go(bar.update)
84
+
else:
85
+
go(lambda x: None)
86
+
open("/tmp/all.json", "w").write(json.dumps(fetched, indent=4))
+51
twitter_to_sqlite/utils.py
+51
twitter_to_sqlite/utils.py
···
1
+
from requests_oauthlib import OAuth1Session
2
+
import time
3
+
import urllib.parse
4
+
5
+
6
+
def session_for_auth(auth):
7
+
return OAuth1Session(
8
+
client_key=auth["api_key"],
9
+
client_secret=auth["api_secret_key"],
10
+
resource_owner_key=auth["access_token"],
11
+
resource_owner_secret=auth["access_token_secret"],
12
+
)
13
+
14
+
15
+
def fetch_follower_chunks(session, user_id, screen_name):
16
+
cursor = -1
17
+
users = []
18
+
while cursor:
19
+
headers, body = fetch_followers(session, cursor, user_id, screen_name)
20
+
yield body["users"]
21
+
cursor = body["next_cursor"]
22
+
time.sleep(61) # Rate limit = 15 per 15 minutes!
23
+
24
+
25
+
def fetch_followers(session, cursor, user_id, screen_name):
26
+
args = {"count": 200, "cursor": cursor}
27
+
if user_id:
28
+
args["user_id"] = user_id
29
+
if screen_name:
30
+
args["screen_name"] = screen_name
31
+
r = session.get(
32
+
"https://api.twitter.com/1.1/followers/list.json?"
33
+
+ urllib.parse.urlencode(args)
34
+
)
35
+
return r.headers, r.json()
36
+
37
+
38
+
def get_profile(session, user_id, screen_name):
39
+
if not (user_id or screen_name):
40
+
return session.get(
41
+
"https://api.twitter.com/1.1/account/verify_credentials.json"
42
+
).json()
43
+
args = {}
44
+
if user_id:
45
+
args["user_id"] = user_id
46
+
if screen_name:
47
+
args["screen_name"] = screen_name
48
+
url = "https://api.twitter.com/1.1/users/show.json"
49
+
if args:
50
+
url += "?" + urllib.parse.urlencode(args)
51
+
return session.get(url).json()