fb_scraper_request 0.2.0__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.
- fb_scraper_request-0.2.0/LICENSE +19 -0
- fb_scraper_request-0.2.0/PKG-INFO +292 -0
- fb_scraper_request-0.2.0/README.md +256 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/__init__.py +14 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/base/__init__.py +0 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/base/base_page.py +90 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/example.py +26 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/facebook_graphql_scraper.py +304 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/pages/__init__.py +0 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/pages/page_optional.py +127 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/tests/__init__.py +0 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/utils/__init__.py +0 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/utils/locator.py +54 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/utils/parser.py +118 -0
- fb_scraper_request-0.2.0/fb_graphql_scraper/utils/utils.py +318 -0
- fb_scraper_request-0.2.0/fb_scraper_request.egg-info/PKG-INFO +292 -0
- fb_scraper_request-0.2.0/fb_scraper_request.egg-info/SOURCES.txt +21 -0
- fb_scraper_request-0.2.0/fb_scraper_request.egg-info/dependency_links.txt +1 -0
- fb_scraper_request-0.2.0/fb_scraper_request.egg-info/requires.txt +7 -0
- fb_scraper_request-0.2.0/fb_scraper_request.egg-info/top_level.txt +1 -0
- fb_scraper_request-0.2.0/pyproject.toml +43 -0
- fb_scraper_request-0.2.0/setup.cfg +4 -0
- fb_scraper_request-0.2.0/setup.py +28 -0
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
Copyright (c) <2024> <FaustRen>
|
|
2
|
+
|
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
4
|
+
of this software and associated documentation files (the "Software"), to deal
|
|
5
|
+
in the Software without restriction, including without limitation the rights
|
|
6
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
7
|
+
copies of the Software, and to permit persons to whom the Software is
|
|
8
|
+
furnished to do so, subject to the following conditions:
|
|
9
|
+
|
|
10
|
+
The above copyright notice and this permission notice shall be included in all
|
|
11
|
+
copies or substantial portions of the Software.
|
|
12
|
+
|
|
13
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
14
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
15
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
16
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
17
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
18
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
|
19
|
+
SOFTWARE.
|
|
@@ -0,0 +1,292 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: fb_scraper_request
|
|
3
|
+
Version: 0.2.0
|
|
4
|
+
Summary: Facebook GraphQL Scraper - No login required, simple API to scrape public Facebook posts
|
|
5
|
+
Home-page: https://github.com/FaustRen/FB_graphql_scraper
|
|
6
|
+
Author: FaustRen
|
|
7
|
+
Author-email: Quang Nguyen <your.email@example.com>
|
|
8
|
+
License: MIT
|
|
9
|
+
Project-URL: Homepage, https://github.com/quangnguyen/facebook-graphql-scraper
|
|
10
|
+
Project-URL: Repository, https://github.com/quangnguyen/facebook-graphql-scraper
|
|
11
|
+
Project-URL: Issues, https://github.com/quangnguyen/facebook-graphql-scraper/issues
|
|
12
|
+
Keywords: facebook,scraper,graphql,social-media,crawler
|
|
13
|
+
Classifier: Development Status :: 4 - Beta
|
|
14
|
+
Classifier: Intended Audience :: Developers
|
|
15
|
+
Classifier: License :: OSI Approved :: MIT License
|
|
16
|
+
Classifier: Programming Language :: Python :: 3
|
|
17
|
+
Classifier: Programming Language :: Python :: 3.9
|
|
18
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
19
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
20
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
21
|
+
Classifier: Topic :: Internet :: WWW/HTTP
|
|
22
|
+
Classifier: Topic :: Software Development :: Libraries :: Python Modules
|
|
23
|
+
Requires-Python: >=3.11
|
|
24
|
+
Description-Content-Type: text/markdown
|
|
25
|
+
License-File: LICENSE
|
|
26
|
+
Requires-Dist: pandas>=2.0.0
|
|
27
|
+
Requires-Dist: requests>=2.28.0
|
|
28
|
+
Requires-Dist: pytz
|
|
29
|
+
Provides-Extra: dev
|
|
30
|
+
Requires-Dist: build>=0.8.0; extra == "dev"
|
|
31
|
+
Requires-Dist: twine>=4.0.0; extra == "dev"
|
|
32
|
+
Dynamic: author
|
|
33
|
+
Dynamic: home-page
|
|
34
|
+
Dynamic: license-file
|
|
35
|
+
Dynamic: requires-python
|
|
36
|
+
|
|
37
|
+
# Facebook GraphQL Scraper
|
|
38
|
+
|
|
39
|
+
Scrape public Facebook posts without login.
|
|
40
|
+
|
|
41
|
+
## Install
|
|
42
|
+
|
|
43
|
+
```bash
|
|
44
|
+
pip install fb-graphql-scraper-simple
|
|
45
|
+
```
|
|
46
|
+
|
|
47
|
+
## Usage
|
|
48
|
+
|
|
49
|
+
```python
|
|
50
|
+
from facebook_graphql_scraper import FacebookGraphqlScraper
|
|
51
|
+
|
|
52
|
+
fb = FacebookGraphqlScraper()
|
|
53
|
+
result = fb.get_user_posts("vietgiaitri", days_limit=3)
|
|
54
|
+
|
|
55
|
+
for post in result["data"]:
|
|
56
|
+
print(post["context"])
|
|
57
|
+
print(f"Likes: {post['reaction_count.count']}")
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
## API
|
|
61
|
+
|
|
62
|
+
- `FacebookGraphqlScraper()` - Create scraper (no params)
|
|
63
|
+
- `get_user_posts(username_or_id, days_limit=61)` - Scrape posts
|
|
64
|
+
|
|
65
|
+
Returns dict with `data` (posts list), `profile` (name), `fb_username_or_userid`.
|
|
66
|
+
|
|
67
|
+
## Requirements
|
|
68
|
+
|
|
69
|
+
Python 3.9+, pandas>=2.0.0, requests>=2.28.0
|
|
70
|
+
|
|
71
|
+
# Support Me
|
|
72
|
+
|
|
73
|
+
If you enjoy this project and would like to support me, please consider donating 🙌
|
|
74
|
+
Your support will help me continue developing this project and working on other exciting ideas!
|
|
75
|
+
|
|
76
|
+
## 💖 Ways to Support:
|
|
77
|
+
|
|
78
|
+
- **PayPal**: [https://www.paypal.me/faustren1z](https://www.paypal.me/faustren1z)
|
|
79
|
+
- **Buy Me a Coffee**: [https://buymeacoffee.com/faustren1z](https://buymeacoffee.com/faustren1z)
|
|
80
|
+
|
|
81
|
+
Thank you for your support!! 🎉
|
|
82
|
+
|
|
83
|
+
### Usage
|
|
84
|
+
|
|
85
|
+
You can choose between two methods to collect user posts data.
|
|
86
|
+
- **Pleas setup driver path at first**
|
|
87
|
+
- **Log in with your account credentials**: login facebook account
|
|
88
|
+
- **Without logging in**: Without logging in, click the X icon to
|
|
89
|
+
- **Difference**: The difference between these two methods is that for some personal accounts, you cannot browse the user's posts without logging into a Facebook account.
|
|
90
|
+
|
|
91
|
+
```python
|
|
92
|
+
# -*- coding: utf-8 -*-
|
|
93
|
+
from fb_graphql_scraper.facebook_graphql_scraper import FacebookGraphqlScraper as fb_graphql_scraper
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
## Example.1 - without logging in
|
|
97
|
+
if __name__ == "__main__":
|
|
98
|
+
facebook_user_name = "love.yuweishao"
|
|
99
|
+
facebook_user_id = "100044253168423"
|
|
100
|
+
days_limit = 100 # Number of days within which to scrape posts
|
|
101
|
+
driver_path = "/Users/hongshangren/Downloads/chromedriver-mac-arm64_136/chromedriver"
|
|
102
|
+
fb_spider = fb_graphql_scraper(driver_path=driver_path, open_browser=False)
|
|
103
|
+
res = fb_spider.get_user_posts(fb_username_or_userid=facebook_user_id, days_limit=days_limit,display_progress=True)
|
|
104
|
+
# print(res)
|
|
105
|
+
|
|
106
|
+
|
|
107
|
+
## Example.2 - login in your facebook account to collect data
|
|
108
|
+
# if __name__ == "__main__":
|
|
109
|
+
# facebook_user_name = "love.yuweishao"
|
|
110
|
+
# facebook_user_id = "100044253168423"
|
|
111
|
+
# fb_account = "facebook_account"
|
|
112
|
+
# fb_pwd = "facebook_paswword"
|
|
113
|
+
# days_limit = 30 # Number of days within which to scrape posts
|
|
114
|
+
# driver_path = "/Users/hongshangren/Downloads/chromedriver-mac-arm64_136/chromedriver"
|
|
115
|
+
# fb_spider = fb_graphql_scraper(fb_account=fb_account,fb_pwd=fb_pwd, driver_path=driver_path, open_browser=False)
|
|
116
|
+
# res = fb_spider.get_user_posts(fb_username_or_userid=facebook_user_name, days_limit=days_limit,display_progress=True)
|
|
117
|
+
# print(res)
|
|
118
|
+
|
|
119
|
+
|
|
120
|
+
|
|
121
|
+
```
|
|
122
|
+
|
|
123
|
+
### Optional parameters
|
|
124
|
+
|
|
125
|
+
- **display_progress**:
|
|
126
|
+
A boolean value (`True` or `False`).
|
|
127
|
+
If set to `True`, the scraper will display how many days of posts remain to be collected based on your `days_limit`.
|
|
128
|
+
For example, if `days_limit=180`, it will scrape posts from today back to 180 days ago.
|
|
129
|
+
During the process, the remaining days will be printed and decrease gradually until reaching 0 or below, at which point scraping stops.
|
|
130
|
+
Example output:
|
|
131
|
+
`439 more days of posts to collect.`
|
|
132
|
+
|
|
133
|
+
- **open_browser**:
|
|
134
|
+
If set to `True`, the scraper will launch a browser window.
|
|
135
|
+
This allows login-based scraping (if `fb_account` and `fb_pwd` are provided), which may access more content.
|
|
136
|
+
However, this mode consumes more memory and **does not guarantee that your Facebook account will avoid being blocked**.
|
|
137
|
+
It is also useful for debugging if scraping fails or unexpected behavior occurs.
|
|
138
|
+
|
|
139
|
+
- **fb_username_or_userid**:
|
|
140
|
+
The Facebook Group ID, Fan Page ID, User ID, or User Name to scrape posts from.
|
|
141
|
+
|
|
142
|
+
- **days_limit**:
|
|
143
|
+
The number of days of posts to retrieve, counting backwards from today.
|
|
144
|
+
|
|
145
|
+
- **fb_account**:
|
|
146
|
+
Your Facebook account (Login-based scraping is still under maintenance.)
|
|
147
|
+
|
|
148
|
+
- **fb_pwd**:
|
|
149
|
+
Your Facebook account password (Login-based scraping is still under maintenance.)
|
|
150
|
+
|
|
151
|
+
|
|
152
|
+
|
|
153
|
+
## Result example
|
|
154
|
+
|
|
155
|
+
```python
|
|
156
|
+
{'fb_username_or_userid': '100044253168423',
|
|
157
|
+
'profile': ['任何工作事宜請洽 高先生',
|
|
158
|
+
'聯絡信箱：hawa00328@gmail.com',
|
|
159
|
+
'聯絡電話：0975-386-266',
|
|
160
|
+
'Page',
|
|
161
|
+
' · 演員',
|
|
162
|
+
'hawa00328@gmail.com',
|
|
163
|
+
'Not yet rated (0 Reviews)',
|
|
164
|
+
'\ufeff',
|
|
165
|
+
'1,484,829 followers'],
|
|
166
|
+
'data': [{'post_id': '1245565493595211',
|
|
167
|
+
'post_url': 'https://www.facebook.com/1245565493595211',
|
|
168
|
+
'username_or_userid': '100044253168423',
|
|
169
|
+
'owing_profile': {'__typename': 'User',
|
|
170
|
+
'name': '邵雨薇',
|
|
171
|
+
'short_name': '邵雨薇',
|
|
172
|
+
'id': '100044253168423'},
|
|
173
|
+
'published_date': Timestamp('2025-05-09 09:14:42'),
|
|
174
|
+
'published_date2': '2025-05-09',
|
|
175
|
+
'time': 1746782082,
|
|
176
|
+
'reaction_count.count': 3566,
|
|
177
|
+
'comment_rendering_instance.comments.total_count': 55,
|
|
178
|
+
'share_count.count': 13,
|
|
179
|
+
'sub_reactions': {'讚': 3273, '大心': 283, '加油': 6, '哈': 2, '哇': 2},
|
|
180
|
+
'context': '溫柔的大貓咪\n緬因貓～～～～～～\n好喜歡❤️❤️❤️',
|
|
181
|
+
'video_view_count': None},
|
|
182
|
+
{'post_id': '1243688160449611',
|
|
183
|
+
'post_url': 'https://www.facebook.com/1243688160449611',
|
|
184
|
+
'username_or_userid': '100044253168423',
|
|
185
|
+
'owing_profile': {'__typename': 'User',
|
|
186
|
+
'name': '邵雨薇',
|
|
187
|
+
'short_name': '邵雨薇',
|
|
188
|
+
'id': '100044253168423'},
|
|
189
|
+
'published_date': Timestamp('2025-05-06 12:38:46'),
|
|
190
|
+
'published_date2': '2025-05-06',
|
|
191
|
+
'time': 1746535126,
|
|
192
|
+
'reaction_count.count': 3270,
|
|
193
|
+
'comment_rendering_instance.comments.total_count': 59,
|
|
194
|
+
'share_count.count': 22,
|
|
195
|
+
'sub_reactions': {'讚': 2978, '大心': 282, '加油': 8, '哈': 2},
|
|
196
|
+
'context': '💛',
|
|
197
|
+
'video_view_count': None},
|
|
198
|
+
{'post_id': '1242879413863819',
|
|
199
|
+
'post_url': 'https://www.facebook.com/1242879413863819',
|
|
200
|
+
'username_or_userid': '100044253168423',
|
|
201
|
+
'owing_profile': {'__typename': 'User',
|
|
202
|
+
'name': '邵雨薇',
|
|
203
|
+
'short_name': '邵雨薇',
|
|
204
|
+
'id': '100044253168423'},
|
|
205
|
+
'published_date': Timestamp('2025-05-05 10:02:32'),
|
|
206
|
+
'published_date2': '2025-05-05',
|
|
207
|
+
'time': 1746439352,
|
|
208
|
+
'reaction_count.count': 3868,
|
|
209
|
+
'comment_rendering_instance.comments.total_count': 55,
|
|
210
|
+
'share_count.count': 28,
|
|
211
|
+
'sub_reactions': {'讚': 3493, '大心': 362, '加油': 9, '哈': 3, '哇': 1},
|
|
212
|
+
'context': '愛的表達方式有很多，\n真誠言語直接的愛、\n以行動表達溫度的愛，\n又或是充滿美麗魔法的愛！ \n\n母親節就給媽媽一份加滿心意以及滿滿美麗的禮物吧！\n#潤姬桃子 的愛的魔法\n祝媽媽母親節快樂💗\n\n@uruhime.momoko.official',
|
|
213
|
+
'video_view_count': None},
|
|
214
|
+
{'post_id': '1239140660904361',
|
|
215
|
+
'post_url': 'https://www.facebook.com/1239140660904361',
|
|
216
|
+
'username_or_userid': '100044253168423',
|
|
217
|
+
'owing_profile': {'__typename': 'User',
|
|
218
|
+
'name': '邵雨薇',
|
|
219
|
+
'short_name': '邵雨薇',
|
|
220
|
+
'id': '100044253168423'},
|
|
221
|
+
'published_date': Timestamp('2025-04-30 09:01:18'),
|
|
222
|
+
'published_date2': '2025-04-30',
|
|
223
|
+
'time': 1746003678,
|
|
224
|
+
'reaction_count.count': 3455,
|
|
225
|
+
'comment_rendering_instance.comments.total_count': 42,
|
|
226
|
+
'share_count.count': 12,
|
|
227
|
+
'sub_reactions': {'讚': 3249, '大心': 199, '哈': 4, '加油': 2, '哇': 1},
|
|
228
|
+
'context': '紐約碎片。\n\n沒注意到主人在，\n拍完往後轉抖了一大下。\n點點頭🙂\u200d↕️對了主人比個大拇指（意義不明？）',
|
|
229
|
+
'video_view_count': None},
|
|
230
|
+
{'post_id': '1237090651109362',
|
|
231
|
+
'post_url': 'https://www.facebook.com/1237090651109362',
|
|
232
|
+
'username_or_userid': '100044253168423',
|
|
233
|
+
'owing_profile': {'__typename': 'User',
|
|
234
|
+
'name': '邵雨薇',
|
|
235
|
+
'short_name': '邵雨薇',
|
|
236
|
+
'id': '100044253168423'},
|
|
237
|
+
'published_date': Timestamp('2025-04-27 12:56:19'),
|
|
238
|
+
'published_date2': '2025-04-27',
|
|
239
|
+
'time': 1745758579,
|
|
240
|
+
'reaction_count.count': 4682,
|
|
241
|
+
'comment_rendering_instance.comments.total_count': 25,
|
|
242
|
+
'share_count.count': 12,
|
|
243
|
+
'sub_reactions': {'讚': 4354, '大心': 311, '加油': 11, '哈': 5, '哇': 1},
|
|
244
|
+
'context': '回家抱老迪 （請自動忽略阿爸）\n迪底撿回來也11年了，希望你也健康幸福。\n希望家人們都平安健康快樂。\n\n#迪底是阿筆的第一個兄弟',
|
|
245
|
+
'video_view_count': None},
|
|
246
|
+
{'post_id': '1236471601171267',
|
|
247
|
+
'post_url': 'https://www.facebook.com/1236471601171267',
|
|
248
|
+
'username_or_userid': '100044253168423',
|
|
249
|
+
'owing_profile': {'__typename': 'User',
|
|
250
|
+
'name': '邵雨薇',
|
|
251
|
+
'short_name': '邵雨薇',
|
|
252
|
+
'id': '100044253168423'},
|
|
253
|
+
'published_date': Timestamp('2025-04-26 16:23:29'),
|
|
254
|
+
'published_date2': '2025-04-26',
|
|
255
|
+
'time': 1745684609,
|
|
256
|
+
'reaction_count.count': 3004,
|
|
257
|
+
'comment_rendering_instance.comments.total_count': 41,
|
|
258
|
+
'share_count.count': 13,
|
|
259
|
+
'sub_reactions': {'讚': 2789, '大心': 210, '哈': 3, '加油': 2},
|
|
260
|
+
'context': '剛在坐高鐵時，覺得時間實在是過得太快了。\n還來不及消化感受些什麼，轉頭又得先離開。\n一天當三天用確實感覺很精彩，\n但是不是錯過太多細節了呢？ 晚安',
|
|
261
|
+
'video_view_count': None},
|
|
262
|
+
{'post_id': '1235381784613582',
|
|
263
|
+
'post_url': 'https://www.facebook.com/1235381784613582',
|
|
264
|
+
'username_or_userid': '100044253168423',
|
|
265
|
+
'owing_profile': {'__typename': 'User',
|
|
266
|
+
'name': '邵雨薇',
|
|
267
|
+
'short_name': '邵雨薇',
|
|
268
|
+
'id': '100044253168423'},
|
|
269
|
+
'published_date': Timestamp('2025-04-25 05:49:56'),
|
|
270
|
+
'published_date2': '2025-04-25',
|
|
271
|
+
'time': 1745560196,
|
|
272
|
+
'reaction_count.count': 6846,
|
|
273
|
+
'comment_rendering_instance.comments.total_count': 101,
|
|
274
|
+
'share_count.count': 40,
|
|
275
|
+
'sub_reactions': {'讚': 6405, '大心': 408, '加油': 19, '哈': 14},
|
|
276
|
+
'context': '偶爾需要遇見一道彩虹，\n雨後剛轉天晴時，就像一個新希望。',
|
|
277
|
+
'video_view_count': None}
|
|
278
|
+
]
|
|
279
|
+
}
|
|
280
|
+
```
|
|
281
|
+
|
|
282
|
+
### Notes
|
|
283
|
+
- If you choose to collect data by logging into your account, you may face the risk of your account being blocked, even if this program only scrolls through Facebook web pages.
|
|
284
|
+
- Reaction Categories (EN): [`like`, `haha`, `angry`, `love`, `care`, `wow`, `sad`]
|
|
285
|
+
- Reaction Categories (TW): [`讚`, `哈`, `怒`, `大心`, `加油`, `哇`, `嗚`]
|
|
286
|
+
|
|
287
|
+
|
|
288
|
+
```python
|
|
289
|
+
|
|
290
|
+
## To-Do
|
|
291
|
+
|
|
292
|
+
- Login-based scraping
|
|
@@ -0,0 +1,256 @@
|
|
|
1
|
+
# Facebook GraphQL Scraper
|
|
2
|
+
|
|
3
|
+
Scrape public Facebook posts without login.
|
|
4
|
+
|
|
5
|
+
## Install
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
pip install fb-graphql-scraper-simple
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
## Usage
|
|
12
|
+
|
|
13
|
+
```python
|
|
14
|
+
from facebook_graphql_scraper import FacebookGraphqlScraper
|
|
15
|
+
|
|
16
|
+
fb = FacebookGraphqlScraper()
|
|
17
|
+
result = fb.get_user_posts("vietgiaitri", days_limit=3)
|
|
18
|
+
|
|
19
|
+
for post in result["data"]:
|
|
20
|
+
print(post["context"])
|
|
21
|
+
print(f"Likes: {post['reaction_count.count']}")
|
|
22
|
+
```
|
|
23
|
+
|
|
24
|
+
## API
|
|
25
|
+
|
|
26
|
+
- `FacebookGraphqlScraper()` - Create scraper (no params)
|
|
27
|
+
- `get_user_posts(username_or_id, days_limit=61)` - Scrape posts
|
|
28
|
+
|
|
29
|
+
Returns dict with `data` (posts list), `profile` (name), `fb_username_or_userid`.
|
|
30
|
+
|
|
31
|
+
## Requirements
|
|
32
|
+
|
|
33
|
+
Python 3.9+, pandas>=2.0.0, requests>=2.28.0
|
|
34
|
+
|
|
35
|
+
# Support Me
|
|
36
|
+
|
|
37
|
+
If you enjoy this project and would like to support me, please consider donating 🙌
|
|
38
|
+
Your support will help me continue developing this project and working on other exciting ideas!
|
|
39
|
+
|
|
40
|
+
## 💖 Ways to Support:
|
|
41
|
+
|
|
42
|
+
- **PayPal**: [https://www.paypal.me/faustren1z](https://www.paypal.me/faustren1z)
|
|
43
|
+
- **Buy Me a Coffee**: [https://buymeacoffee.com/faustren1z](https://buymeacoffee.com/faustren1z)
|
|
44
|
+
|
|
45
|
+
Thank you for your support!! 🎉
|
|
46
|
+
|
|
47
|
+
### Usage
|
|
48
|
+
|
|
49
|
+
You can choose between two methods to collect user posts data.
|
|
50
|
+
- **Pleas setup driver path at first**
|
|
51
|
+
- **Log in with your account credentials**: login facebook account
|
|
52
|
+
- **Without logging in**: Without logging in, click the X icon to
|
|
53
|
+
- **Difference**: The difference between these two methods is that for some personal accounts, you cannot browse the user's posts without logging into a Facebook account.
|
|
54
|
+
|
|
55
|
+
```python
|
|
56
|
+
# -*- coding: utf-8 -*-
|
|
57
|
+
from fb_graphql_scraper.facebook_graphql_scraper import FacebookGraphqlScraper as fb_graphql_scraper
|
|
58
|
+
|
|
59
|
+
|
|
60
|
+
## Example.1 - without logging in
|
|
61
|
+
if __name__ == "__main__":
|
|
62
|
+
facebook_user_name = "love.yuweishao"
|
|
63
|
+
facebook_user_id = "100044253168423"
|
|
64
|
+
days_limit = 100 # Number of days within which to scrape posts
|
|
65
|
+
driver_path = "/Users/hongshangren/Downloads/chromedriver-mac-arm64_136/chromedriver"
|
|
66
|
+
fb_spider = fb_graphql_scraper(driver_path=driver_path, open_browser=False)
|
|
67
|
+
res = fb_spider.get_user_posts(fb_username_or_userid=facebook_user_id, days_limit=days_limit,display_progress=True)
|
|
68
|
+
# print(res)
|
|
69
|
+
|
|
70
|
+
|
|
71
|
+
## Example.2 - login in your facebook account to collect data
|
|
72
|
+
# if __name__ == "__main__":
|
|
73
|
+
# facebook_user_name = "love.yuweishao"
|
|
74
|
+
# facebook_user_id = "100044253168423"
|
|
75
|
+
# fb_account = "facebook_account"
|
|
76
|
+
# fb_pwd = "facebook_paswword"
|
|
77
|
+
# days_limit = 30 # Number of days within which to scrape posts
|
|
78
|
+
# driver_path = "/Users/hongshangren/Downloads/chromedriver-mac-arm64_136/chromedriver"
|
|
79
|
+
# fb_spider = fb_graphql_scraper(fb_account=fb_account,fb_pwd=fb_pwd, driver_path=driver_path, open_browser=False)
|
|
80
|
+
# res = fb_spider.get_user_posts(fb_username_or_userid=facebook_user_name, days_limit=days_limit,display_progress=True)
|
|
81
|
+
# print(res)
|
|
82
|
+
|
|
83
|
+
|
|
84
|
+
|
|
85
|
+
```
|
|
86
|
+
|
|
87
|
+
### Optional parameters
|
|
88
|
+
|
|
89
|
+
- **display_progress**:
|
|
90
|
+
A boolean value (`True` or `False`).
|
|
91
|
+
If set to `True`, the scraper will display how many days of posts remain to be collected based on your `days_limit`.
|
|
92
|
+
For example, if `days_limit=180`, it will scrape posts from today back to 180 days ago.
|
|
93
|
+
During the process, the remaining days will be printed and decrease gradually until reaching 0 or below, at which point scraping stops.
|
|
94
|
+
Example output:
|
|
95
|
+
`439 more days of posts to collect.`
|
|
96
|
+
|
|
97
|
+
- **open_browser**:
|
|
98
|
+
If set to `True`, the scraper will launch a browser window.
|
|
99
|
+
This allows login-based scraping (if `fb_account` and `fb_pwd` are provided), which may access more content.
|
|
100
|
+
However, this mode consumes more memory and **does not guarantee that your Facebook account will avoid being blocked**.
|
|
101
|
+
It is also useful for debugging if scraping fails or unexpected behavior occurs.
|
|
102
|
+
|
|
103
|
+
- **fb_username_or_userid**:
|
|
104
|
+
The Facebook Group ID, Fan Page ID, User ID, or User Name to scrape posts from.
|
|
105
|
+
|
|
106
|
+
- **days_limit**:
|
|
107
|
+
The number of days of posts to retrieve, counting backwards from today.
|
|
108
|
+
|
|
109
|
+
- **fb_account**:
|
|
110
|
+
Your Facebook account (Login-based scraping is still under maintenance.)
|
|
111
|
+
|
|
112
|
+
- **fb_pwd**:
|
|
113
|
+
Your Facebook account password (Login-based scraping is still under maintenance.)
|
|
114
|
+
|
|
115
|
+
|
|
116
|
+
|
|
117
|
+
## Result example
|
|
118
|
+
|
|
119
|
+
```python
|
|
120
|
+
{'fb_username_or_userid': '100044253168423',
|
|
121
|
+
'profile': ['任何工作事宜請洽 高先生',
|
|
122
|
+
'聯絡信箱：hawa00328@gmail.com',
|
|
123
|
+
'聯絡電話：0975-386-266',
|
|
124
|
+
'Page',
|
|
125
|
+
' · 演員',
|
|
126
|
+
'hawa00328@gmail.com',
|
|
127
|
+
'Not yet rated (0 Reviews)',
|
|
128
|
+
'\ufeff',
|
|
129
|
+
'1,484,829 followers'],
|
|
130
|
+
'data': [{'post_id': '1245565493595211',
|
|
131
|
+
'post_url': 'https://www.facebook.com/1245565493595211',
|
|
132
|
+
'username_or_userid': '100044253168423',
|
|
133
|
+
'owing_profile': {'__typename': 'User',
|
|
134
|
+
'name': '邵雨薇',
|
|
135
|
+
'short_name': '邵雨薇',
|
|
136
|
+
'id': '100044253168423'},
|
|
137
|
+
'published_date': Timestamp('2025-05-09 09:14:42'),
|
|
138
|
+
'published_date2': '2025-05-09',
|
|
139
|
+
'time': 1746782082,
|
|
140
|
+
'reaction_count.count': 3566,
|
|
141
|
+
'comment_rendering_instance.comments.total_count': 55,
|
|
142
|
+
'share_count.count': 13,
|
|
143
|
+
'sub_reactions': {'讚': 3273, '大心': 283, '加油': 6, '哈': 2, '哇': 2},
|
|
144
|
+
'context': '溫柔的大貓咪\n緬因貓～～～～～～\n好喜歡❤️❤️❤️',
|
|
145
|
+
'video_view_count': None},
|
|
146
|
+
{'post_id': '1243688160449611',
|
|
147
|
+
'post_url': 'https://www.facebook.com/1243688160449611',
|
|
148
|
+
'username_or_userid': '100044253168423',
|
|
149
|
+
'owing_profile': {'__typename': 'User',
|
|
150
|
+
'name': '邵雨薇',
|
|
151
|
+
'short_name': '邵雨薇',
|
|
152
|
+
'id': '100044253168423'},
|
|
153
|
+
'published_date': Timestamp('2025-05-06 12:38:46'),
|
|
154
|
+
'published_date2': '2025-05-06',
|
|
155
|
+
'time': 1746535126,
|
|
156
|
+
'reaction_count.count': 3270,
|
|
157
|
+
'comment_rendering_instance.comments.total_count': 59,
|
|
158
|
+
'share_count.count': 22,
|
|
159
|
+
'sub_reactions': {'讚': 2978, '大心': 282, '加油': 8, '哈': 2},
|
|
160
|
+
'context': '💛',
|
|
161
|
+
'video_view_count': None},
|
|
162
|
+
{'post_id': '1242879413863819',
|
|
163
|
+
'post_url': 'https://www.facebook.com/1242879413863819',
|
|
164
|
+
'username_or_userid': '100044253168423',
|
|
165
|
+
'owing_profile': {'__typename': 'User',
|
|
166
|
+
'name': '邵雨薇',
|
|
167
|
+
'short_name': '邵雨薇',
|
|
168
|
+
'id': '100044253168423'},
|
|
169
|
+
'published_date': Timestamp('2025-05-05 10:02:32'),
|
|
170
|
+
'published_date2': '2025-05-05',
|
|
171
|
+
'time': 1746439352,
|
|
172
|
+
'reaction_count.count': 3868,
|
|
173
|
+
'comment_rendering_instance.comments.total_count': 55,
|
|
174
|
+
'share_count.count': 28,
|
|
175
|
+
'sub_reactions': {'讚': 3493, '大心': 362, '加油': 9, '哈': 3, '哇': 1},
|
|
176
|
+
'context': '愛的表達方式有很多，\n真誠言語直接的愛、\n以行動表達溫度的愛，\n又或是充滿美麗魔法的愛！ \n\n母親節就給媽媽一份加滿心意以及滿滿美麗的禮物吧！\n#潤姬桃子 的愛的魔法\n祝媽媽母親節快樂💗\n\n@uruhime.momoko.official',
|
|
177
|
+
'video_view_count': None},
|
|
178
|
+
{'post_id': '1239140660904361',
|
|
179
|
+
'post_url': 'https://www.facebook.com/1239140660904361',
|
|
180
|
+
'username_or_userid': '100044253168423',
|
|
181
|
+
'owing_profile': {'__typename': 'User',
|
|
182
|
+
'name': '邵雨薇',
|
|
183
|
+
'short_name': '邵雨薇',
|
|
184
|
+
'id': '100044253168423'},
|
|
185
|
+
'published_date': Timestamp('2025-04-30 09:01:18'),
|
|
186
|
+
'published_date2': '2025-04-30',
|
|
187
|
+
'time': 1746003678,
|
|
188
|
+
'reaction_count.count': 3455,
|
|
189
|
+
'comment_rendering_instance.comments.total_count': 42,
|
|
190
|
+
'share_count.count': 12,
|
|
191
|
+
'sub_reactions': {'讚': 3249, '大心': 199, '哈': 4, '加油': 2, '哇': 1},
|
|
192
|
+
'context': '紐約碎片。\n\n沒注意到主人在，\n拍完往後轉抖了一大下。\n點點頭🙂\u200d↕️對了主人比個大拇指（意義不明？）',
|
|
193
|
+
'video_view_count': None},
|
|
194
|
+
{'post_id': '1237090651109362',
|
|
195
|
+
'post_url': 'https://www.facebook.com/1237090651109362',
|
|
196
|
+
'username_or_userid': '100044253168423',
|
|
197
|
+
'owing_profile': {'__typename': 'User',
|
|
198
|
+
'name': '邵雨薇',
|
|
199
|
+
'short_name': '邵雨薇',
|
|
200
|
+
'id': '100044253168423'},
|
|
201
|
+
'published_date': Timestamp('2025-04-27 12:56:19'),
|
|
202
|
+
'published_date2': '2025-04-27',
|
|
203
|
+
'time': 1745758579,
|
|
204
|
+
'reaction_count.count': 4682,
|
|
205
|
+
'comment_rendering_instance.comments.total_count': 25,
|
|
206
|
+
'share_count.count': 12,
|
|
207
|
+
'sub_reactions': {'讚': 4354, '大心': 311, '加油': 11, '哈': 5, '哇': 1},
|
|
208
|
+
'context': '回家抱老迪 （請自動忽略阿爸）\n迪底撿回來也11年了，希望你也健康幸福。\n希望家人們都平安健康快樂。\n\n#迪底是阿筆的第一個兄弟',
|
|
209
|
+
'video_view_count': None},
|
|
210
|
+
{'post_id': '1236471601171267',
|
|
211
|
+
'post_url': 'https://www.facebook.com/1236471601171267',
|
|
212
|
+
'username_or_userid': '100044253168423',
|
|
213
|
+
'owing_profile': {'__typename': 'User',
|
|
214
|
+
'name': '邵雨薇',
|
|
215
|
+
'short_name': '邵雨薇',
|
|
216
|
+
'id': '100044253168423'},
|
|
217
|
+
'published_date': Timestamp('2025-04-26 16:23:29'),
|
|
218
|
+
'published_date2': '2025-04-26',
|
|
219
|
+
'time': 1745684609,
|
|
220
|
+
'reaction_count.count': 3004,
|
|
221
|
+
'comment_rendering_instance.comments.total_count': 41,
|
|
222
|
+
'share_count.count': 13,
|
|
223
|
+
'sub_reactions': {'讚': 2789, '大心': 210, '哈': 3, '加油': 2},
|
|
224
|
+
'context': '剛在坐高鐵時，覺得時間實在是過得太快了。\n還來不及消化感受些什麼，轉頭又得先離開。\n一天當三天用確實感覺很精彩，\n但是不是錯過太多細節了呢？ 晚安',
|
|
225
|
+
'video_view_count': None},
|
|
226
|
+
{'post_id': '1235381784613582',
|
|
227
|
+
'post_url': 'https://www.facebook.com/1235381784613582',
|
|
228
|
+
'username_or_userid': '100044253168423',
|
|
229
|
+
'owing_profile': {'__typename': 'User',
|
|
230
|
+
'name': '邵雨薇',
|
|
231
|
+
'short_name': '邵雨薇',
|
|
232
|
+
'id': '100044253168423'},
|
|
233
|
+
'published_date': Timestamp('2025-04-25 05:49:56'),
|
|
234
|
+
'published_date2': '2025-04-25',
|
|
235
|
+
'time': 1745560196,
|
|
236
|
+
'reaction_count.count': 6846,
|
|
237
|
+
'comment_rendering_instance.comments.total_count': 101,
|
|
238
|
+
'share_count.count': 40,
|
|
239
|
+
'sub_reactions': {'讚': 6405, '大心': 408, '加油': 19, '哈': 14},
|
|
240
|
+
'context': '偶爾需要遇見一道彩虹，\n雨後剛轉天晴時，就像一個新希望。',
|
|
241
|
+
'video_view_count': None}
|
|
242
|
+
]
|
|
243
|
+
}
|
|
244
|
+
```
|
|
245
|
+
|
|
246
|
+
### Notes
|
|
247
|
+
- If you choose to collect data by logging into your account, you may face the risk of your account being blocked, even if this program only scrolls through Facebook web pages.
|
|
248
|
+
- Reaction Categories (EN): [`like`, `haha`, `angry`, `love`, `care`, `wow`, `sad`]
|
|
249
|
+
- Reaction Categories (TW): [`讚`, `哈`, `怒`, `大心`, `加油`, `哇`, `嗚`]
|
|
250
|
+
|
|
251
|
+
|
|
252
|
+
```python
|
|
253
|
+
|
|
254
|
+
## To-Do
|
|
255
|
+
|
|
256
|
+
- Login-based scraping
|
|
@@ -0,0 +1,14 @@
|
|
|
1
|
+
"""Facebook GraphQL Scraper - Simple API to scrape public Facebook posts without login.
|
|
2
|
+
|
|
3
|
+
Example:
|
|
4
|
+
from facebook_graphql_scraper import FacebookGraphqlScraper
|
|
5
|
+
|
|
6
|
+
fb = FacebookGraphqlScraper()
|
|
7
|
+
result = fb.get_user_posts("vietgiaitri", days_limit=3)
|
|
8
|
+
print(result["data"])
|
|
9
|
+
"""
|
|
10
|
+
|
|
11
|
+
from .facebook_graphql_scraper import FacebookGraphqlScraper
|
|
12
|
+
|
|
13
|
+
__version__ = "0.2.0"
|
|
14
|
+
__all__ = ["FacebookGraphqlScraper"]
|
|
File without changes
|
|
@@ -0,0 +1,90 @@
|
|
|
1
|
+
# -*- coding:utf-8 -*-
|
|
2
|
+
from selenium.webdriver.chrome.options import Options as ChromeOptions
|
|
3
|
+
from selenium.webdriver.chrome.service import Service
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
class BasePage:
|
|
7
|
+
def __init__(self, driver_path: str, open_browser: bool = False):
|
|
8
|
+
chrome_options = self._build_options(open_browser)
|
|
9
|
+
normalized_driver_path = self._normalize_path(driver_path)
|
|
10
|
+
|
|
11
|
+
if self._looks_like_chrome_binary(normalized_driver_path):
|
|
12
|
+
chrome_options.binary_location = normalized_driver_path
|
|
13
|
+
service = Service()
|
|
14
|
+
elif normalized_driver_path:
|
|
15
|
+
service = Service(normalized_driver_path)
|
|
16
|
+
else:
|
|
17
|
+
service = Service()
|
|
18
|
+
|
|
19
|
+
self.driver = self._build_driver(service=service, chrome_options=chrome_options)
|
|
20
|
+
self.driver.maximize_window()
|
|
21
|
+
|
|
22
|
+
@staticmethod
|
|
23
|
+
def _build_options(open_browser: bool) -> ChromeOptions:
|
|
24
|
+
options = ChromeOptions()
|
|
25
|
+
options.add_argument("--disable-blink-features")
|
|
26
|
+
options.add_argument("--disable-notifications")
|
|
27
|
+
options.add_argument("--disable-blink-features=AutomationControlled")
|
|
28
|
+
if not open_browser:
|
|
29
|
+
options.add_argument("--headless=new")
|
|
30
|
+
options.add_argument("--blink-settings=imagesEnabled=false")
|
|
31
|
+
return options
|
|
32
|
+
|
|
33
|
+
@staticmethod
|
|
34
|
+
def _normalize_path(path: str | None) -> str | None:
|
|
35
|
+
if not path:
|
|
36
|
+
return None
|
|
37
|
+
# In notebook strings users often escape spaces (e.g. "Google\ Chrome").
|
|
38
|
+
return path.replace("\\ ", " ").strip()
|
|
39
|
+
|
|
40
|
+
@staticmethod
|
|
41
|
+
def _looks_like_chrome_binary(path: str | None) -> bool:
|
|
42
|
+
if not path:
|
|
43
|
+
return False
|
|
44
|
+
normalized = path.lower()
|
|
45
|
+
return normalized.endswith("/google chrome") or normalized.endswith("/chrome")
|
|
46
|
+
|
|
47
|
+
@staticmethod
|
|
48
|
+
def _build_driver(service: Service, chrome_options: ChromeOptions):
|
|
49
|
+
from seleniumwire import webdriver
|
|
50
|
+
|
|
51
|
+
try:
|
|
52
|
+
return webdriver.Chrome(service=service, options=chrome_options)
|
|
53
|
+
except AttributeError as exc:
|
|
54
|
+
if "VERSION_CHOICES" not in str(exc):
|
|
55
|
+
raise
|
|
56
|
+
# Some selenium-wire/pyOpenSSL combinations expose this at runtime.
|
|
57
|
+
BasePage._patch_seleniumwire_tls_version_choices()
|
|
58
|
+
return webdriver.Chrome(service=service, options=chrome_options)
|
|
59
|
+
|
|
60
|
+
@staticmethod
|
|
61
|
+
def _patch_seleniumwire_tls_version_choices() -> None:
|
|
62
|
+
from OpenSSL import SSL
|
|
63
|
+
from seleniumwire.thirdparty.mitmproxy.net import tls
|
|
64
|
+
|
|
65
|
+
if hasattr(tls, "VERSION_CHOICES"):
|
|
66
|
+
return
|
|
67
|
+
|
|
68
|
+
basic_options = SSL.OP_CIPHER_SERVER_PREFERENCE
|
|
69
|
+
if hasattr(SSL, "OP_NO_COMPRESSION"):
|
|
70
|
+
basic_options |= SSL.OP_NO_COMPRESSION
|
|
71
|
+
|
|
72
|
+
default_method = getattr(SSL, "SSLv23_METHOD", getattr(SSL, "TLS_METHOD", None))
|
|
73
|
+
default_options = basic_options
|
|
74
|
+
if hasattr(SSL, "OP_NO_SSLv2"):
|
|
75
|
+
default_options |= SSL.OP_NO_SSLv2
|
|
76
|
+
if hasattr(SSL, "OP_NO_SSLv3"):
|
|
77
|
+
default_options |= SSL.OP_NO_SSLv3
|
|
78
|
+
|
|
79
|
+
version_choices = {
|
|
80
|
+
"all": (default_method, basic_options),
|
|
81
|
+
"secure": (default_method, default_options),
|
|
82
|
+
}
|
|
83
|
+
|
|
84
|
+
for name in ("TLSv1", "TLSv1_1", "TLSv1_2"):
|
|
85
|
+
method_name = f"{name}_METHOD"
|
|
86
|
+
method = getattr(SSL, method_name, None)
|
|
87
|
+
if method is not None:
|
|
88
|
+
version_choices[name] = (method, basic_options)
|
|
89
|
+
|
|
90
|
+
tls.VERSION_CHOICES = version_choices
|