@@ -31,11 +31,17 @@ anyio==4.3.0
31
31
# via openai
32
32
# via starlette
33
33
# via watchfiles
34
+ astroid==3.2.2
35
+ # via pylint
36
+ async-timeout==4.0.3
37
+ # via aiohttp
38
+ # via langchain
34
39
attrs==23.2.0
35
40
# via aiohttp
36
41
# via jsonschema
37
42
# via referencing
38
43
babel==2.15.0
44
+ # via courlan
39
45
# via sphinx
40
46
beautifulsoup4==4.12.3
41
47
# via furo
@@ -57,22 +63,31 @@ certifi==2024.2.2
57
63
# via httpcore
58
64
# via httpx
59
65
# via requests
66
+ # via trafilatura
60
67
charset-normalizer==3.3.2
68
+ # via htmldate
61
69
# via requests
70
+ # via trafilatura
62
71
click==8.1.7
63
72
# via burr
64
73
# via streamlit
65
74
# via typer
66
75
# via uvicorn
67
76
contourpy==1.2.1
68
77
# via matplotlib
78
+ courlan==1.2.0
79
+ # via trafilatura
69
80
cycler==0.12.1
70
81
# via matplotlib
71
82
dataclasses-json==0.6.6
72
83
# via langchain
73
84
# via langchain-community
85
+ dateparser==1.2.0
86
+ # via htmldate
74
87
defusedxml==0.7.1
75
88
# via langchain-anthropic
89
+ dill==0.3.8
90
+ # via pylint
76
91
distro==1.9.0
77
92
# via anthropic
78
93
# via groq
@@ -83,6 +98,9 @@ docutils==0.19
83
98
# via sphinx
84
99
email-validator==2.1.1
85
100
# via fastapi
101
+ exceptiongroup==1.2.1
102
+ # via anyio
103
+ # via pytest
86
104
faiss-cpu==1.8.0
87
105
# via scrapegraphai
88
106
fastapi==0.111.0
@@ -139,6 +157,7 @@ graphviz==0.20.3
139
157
# via scrapegraphai
140
158
greenlet==3.0.3
141
159
# via playwright
160
+ # via sqlalchemy
142
161
groq==0.8.0
143
162
# via langchain-groq
144
163
grpcio==1.64.0
@@ -151,6 +170,8 @@ h11==0.14.0
151
170
# via uvicorn
152
171
html2text==2024.2.26
153
172
# via scrapegraphai
173
+ htmldate==1.8.1
174
+ # via trafilatura
154
175
httpcore==1.0.5
155
176
# via httpx
156
177
httplib2==0.22.0
@@ -176,8 +197,14 @@ idna==3.7
176
197
# via yarl
177
198
imagesize==1.4.1
178
199
# via sphinx
200
+ importlib-metadata==8.0.0
201
+ # via sphinx
202
+ importlib-resources==6.4.0
203
+ # via matplotlib
179
204
iniconfig==2.0.0
180
205
# via pytest
206
+ isort==5.13.2
207
+ # via pylint
181
208
jinja2==3.1.4
182
209
# via altair
183
210
# via burr
@@ -198,6 +225,8 @@ jsonschema==4.22.0
198
225
# via altair
199
226
jsonschema-specifications==2023.12.1
200
227
# via jsonschema
228
+ justext==3.0.1
229
+ # via trafilatura
201
230
kiwisolver==1.4.5
202
231
# via matplotlib
203
232
langchain==0.1.15
@@ -236,6 +265,12 @@ loguru==0.7.2
236
265
# via burr
237
266
lxml==5.2.2
238
267
# via free-proxy
268
+ # via htmldate
269
+ # via justext
270
+ # via lxml-html-clean
271
+ # via trafilatura
272
+ lxml-html-clean==0.1.1
273
+ # via lxml
239
274
markdown-it-py==3.0.0
240
275
# via rich
241
276
markupsafe==2.1.5
@@ -244,6 +279,8 @@ marshmallow==3.21.2
244
279
# via dataclasses-json
245
280
matplotlib==3.9.0
246
281
# via burr
282
+ mccabe==0.7.0
283
+ # via pylint
247
284
mdurl==0.1.2
248
285
# via markdown-it-py
249
286
minify-html==0.15.0
@@ -291,6 +328,8 @@ pillow==10.3.0
291
328
# via fireworks-ai
292
329
# via matplotlib
293
330
# via streamlit
331
+ platformdirs==4.2.2
332
+ # via pylint
294
333
playwright==1.43.0
295
334
# via scrapegraphai
296
335
# via undetected-playwright
@@ -336,6 +375,7 @@ pygments==2.18.0
336
375
# via furo
337
376
# via rich
338
377
# via sphinx
378
+ pylint==3.2.5
339
379
pyparsing==3.1.2
340
380
# via httplib2
341
381
# via matplotlib
@@ -344,6 +384,8 @@ pytest==8.0.0
344
384
pytest-mock==3.14.0
345
385
python-dateutil==2.9.0.post0
346
386
# via botocore
387
+ # via dateparser
388
+ # via htmldate
347
389
# via matplotlib
348
390
# via pandas
349
391
python-dotenv==1.0.1
@@ -352,6 +394,7 @@ python-dotenv==1.0.1
352
394
python-multipart==0.0.9
353
395
# via fastapi
354
396
pytz==2024.1
397
+ # via dateparser
355
398
# via pandas
356
399
pyyaml==6.0.1
357
400
# via huggingface-hub
@@ -363,6 +406,7 @@ referencing==0.35.1
363
406
# via jsonschema
364
407
# via jsonschema-specifications
365
408
regex==2024.5.15
409
+ # via dateparser
366
410
# via tiktoken
367
411
requests==2.32.2
368
412
# via burr
@@ -439,10 +483,17 @@ tenacity==8.3.0
439
483
tiktoken==0.6.0
440
484
# via langchain-openai
441
485
# via scrapegraphai
486
+ tld==0.13
487
+ # via courlan
442
488
tokenizers==0.19.1
443
489
# via anthropic
444
490
toml==0.10.2
445
491
# via streamlit
492
+ tomli==2.0.1
493
+ # via pylint
494
+ # via pytest
495
+ tomlkit==0.12.5
496
+ # via pylint
446
497
toolz==0.12.1
447
498
# via altair
448
499
tornado==6.4
@@ -453,10 +504,15 @@ tqdm==4.66.4
453
504
# via openai
454
505
# via scrapegraphai
455
506
# via semchunk
507
+ trafilatura==1.10.0
508
+ # via scrapegraphai
456
509
typer==0.12.3
457
510
# via fastapi-cli
458
511
typing-extensions==4.12.0
512
+ # via altair
459
513
# via anthropic
514
+ # via anyio
515
+ # via astroid
460
516
# via fastapi
461
517
# via fastapi-pagination
462
518
# via google-generativeai
@@ -466,16 +522,21 @@ typing-extensions==4.12.0
466
522
# via pydantic
467
523
# via pydantic-core
468
524
# via pyee
525
+ # via pylint
469
526
# via sf-hamilton
470
527
# via sqlalchemy
528
+ # via starlette
471
529
# via streamlit
472
530
# via typer
473
531
# via typing-inspect
532
+ # via uvicorn
474
533
typing-inspect==0.9.0
475
534
# via dataclasses-json
476
535
# via sf-hamilton
477
536
tzdata==2024.1
478
537
# via pandas
538
+ tzlocal==5.2
539
+ # via dateparser
479
540
ujson==5.10.0
480
541
# via fastapi
481
542
undetected-playwright==0.3.0
@@ -484,7 +545,10 @@ uritemplate==4.1.1
484
545
# via google-api-python-client
485
546
urllib3==1.26.18
486
547
# via botocore
548
+ # via courlan
549
+ # via htmldate
487
550
# via requests
551
+ # via trafilatura
488
552
uvicorn==0.29.0
489
553
# via burr
490
554
# via fastapi
@@ -496,3 +560,6 @@ websockets==12.0
496
560
# via uvicorn
497
561
yarl==1.9.4
498
562
# via aiohttp
563
+ zipp==3.19.2
564
+ # via importlib-metadata
565
+ # via importlib-resources
0 commit comments