firecrawl 2.10.0__py3-none-any.whl → 2.11.0__py3-none-any.whl
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.
Potentially problematic release.
This version of firecrawl might be problematic. Click here for more details.
- firecrawl/__init__.py +1 -1
- firecrawl/firecrawl.py +18 -10
- {firecrawl-2.10.0.dist-info → firecrawl-2.11.0.dist-info}/METADATA +1 -1
- {firecrawl-2.10.0.dist-info → firecrawl-2.11.0.dist-info}/RECORD +7 -7
- {firecrawl-2.10.0.dist-info → firecrawl-2.11.0.dist-info}/LICENSE +0 -0
- {firecrawl-2.10.0.dist-info → firecrawl-2.11.0.dist-info}/WHEEL +0 -0
- {firecrawl-2.10.0.dist-info → firecrawl-2.11.0.dist-info}/top_level.txt +0 -0
firecrawl/__init__.py
CHANGED
|
@@ -13,7 +13,7 @@ import os
|
|
|
13
13
|
|
|
14
14
|
from .firecrawl import FirecrawlApp, AsyncFirecrawlApp, JsonConfig, ScrapeOptions, ChangeTrackingOptions # noqa
|
|
15
15
|
|
|
16
|
-
__version__ = "2.
|
|
16
|
+
__version__ = "2.11.0"
|
|
17
17
|
|
|
18
18
|
# Define the logger for the Firecrawl project
|
|
19
19
|
logger: logging.Logger = logging.getLogger("firecrawl")
|
firecrawl/firecrawl.py
CHANGED
|
@@ -96,6 +96,7 @@ class AgentOptionsExtract(pydantic.BaseModel):
|
|
|
96
96
|
class ActionsResult(pydantic.BaseModel):
|
|
97
97
|
"""Result of actions performed during scraping."""
|
|
98
98
|
screenshots: List[str]
|
|
99
|
+
pdfs: List[str]
|
|
99
100
|
|
|
100
101
|
class ChangeTrackingData(pydantic.BaseModel):
|
|
101
102
|
"""
|
|
@@ -172,6 +173,7 @@ class ScreenshotAction(pydantic.BaseModel):
|
|
|
172
173
|
"""Screenshot action to perform during scraping."""
|
|
173
174
|
type: Literal["screenshot"]
|
|
174
175
|
fullPage: Optional[bool] = None
|
|
176
|
+
quality: Optional[int] = None
|
|
175
177
|
|
|
176
178
|
class ClickAction(pydantic.BaseModel):
|
|
177
179
|
"""Click action to perform during scraping."""
|
|
@@ -203,6 +205,12 @@ class ExecuteJavascriptAction(pydantic.BaseModel):
|
|
|
203
205
|
type: Literal["executeJavascript"]
|
|
204
206
|
script: str
|
|
205
207
|
|
|
208
|
+
class PDFAction(pydantic.BaseModel):
|
|
209
|
+
"""PDF action to perform during scraping."""
|
|
210
|
+
type: Literal["pdf"]
|
|
211
|
+
format: Optional[Literal["A0", "A1", "A2", "A3", "A4", "A5", "A6", "Letter", "Legal", "Tabloid", "Ledger"]] = None
|
|
212
|
+
landscape: Optional[bool] = None
|
|
213
|
+
scale: Optional[float] = None
|
|
206
214
|
|
|
207
215
|
class ExtractAgent(pydantic.BaseModel):
|
|
208
216
|
"""Configuration for the agent in extract operations."""
|
|
@@ -219,7 +227,7 @@ class ScrapeParams(ScrapeOptions):
|
|
|
219
227
|
"""Parameters for scraping operations."""
|
|
220
228
|
extract: Optional[JsonConfig] = None
|
|
221
229
|
jsonOptions: Optional[JsonConfig] = None
|
|
222
|
-
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None
|
|
230
|
+
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]] = None
|
|
223
231
|
agent: Optional[AgentOptions] = None
|
|
224
232
|
webhook: Optional[WebhookConfig] = None
|
|
225
233
|
|
|
@@ -469,7 +477,7 @@ class FirecrawlApp:
|
|
|
469
477
|
parse_pdf: Optional[bool] = None,
|
|
470
478
|
extract: Optional[JsonConfig] = None,
|
|
471
479
|
json_options: Optional[JsonConfig] = None,
|
|
472
|
-
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
|
|
480
|
+
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]] = None,
|
|
473
481
|
change_tracking_options: Optional[ChangeTrackingOptions] = None,
|
|
474
482
|
max_age: Optional[int] = None,
|
|
475
483
|
store_in_cache: Optional[bool] = None,
|
|
@@ -493,7 +501,7 @@ class FirecrawlApp:
|
|
|
493
501
|
proxy (Optional[Literal["basic", "stealth", "auto"]]): Proxy type (basic/stealth)
|
|
494
502
|
extract (Optional[JsonConfig]): Content extraction settings
|
|
495
503
|
json_options (Optional[JsonConfig]): JSON extraction settings
|
|
496
|
-
actions (Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]]): Actions to perform
|
|
504
|
+
actions (Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]]): Actions to perform
|
|
497
505
|
change_tracking_options (Optional[ChangeTrackingOptions]): Change tracking settings
|
|
498
506
|
|
|
499
507
|
|
|
@@ -1236,7 +1244,7 @@ class FirecrawlApp:
|
|
|
1236
1244
|
proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
|
|
1237
1245
|
extract: Optional[JsonConfig] = None,
|
|
1238
1246
|
json_options: Optional[JsonConfig] = None,
|
|
1239
|
-
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
|
|
1247
|
+
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]] = None,
|
|
1240
1248
|
agent: Optional[AgentOptions] = None,
|
|
1241
1249
|
poll_interval: Optional[int] = 2,
|
|
1242
1250
|
max_concurrency: Optional[int] = None,
|
|
@@ -1374,7 +1382,7 @@ class FirecrawlApp:
|
|
|
1374
1382
|
proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
|
|
1375
1383
|
extract: Optional[JsonConfig] = None,
|
|
1376
1384
|
json_options: Optional[JsonConfig] = None,
|
|
1377
|
-
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
|
|
1385
|
+
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]] = None,
|
|
1378
1386
|
agent: Optional[AgentOptions] = None,
|
|
1379
1387
|
max_concurrency: Optional[int] = None,
|
|
1380
1388
|
idempotency_key: Optional[str] = None,
|
|
@@ -1510,7 +1518,7 @@ class FirecrawlApp:
|
|
|
1510
1518
|
proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
|
|
1511
1519
|
extract: Optional[JsonConfig] = None,
|
|
1512
1520
|
json_options: Optional[JsonConfig] = None,
|
|
1513
|
-
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
|
|
1521
|
+
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]] = None,
|
|
1514
1522
|
agent: Optional[AgentOptions] = None,
|
|
1515
1523
|
max_concurrency: Optional[int] = None,
|
|
1516
1524
|
idempotency_key: Optional[str] = None,
|
|
@@ -2911,7 +2919,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
|
|
|
2911
2919
|
parse_pdf: Optional[bool] = None,
|
|
2912
2920
|
extract: Optional[JsonConfig] = None,
|
|
2913
2921
|
json_options: Optional[JsonConfig] = None,
|
|
2914
|
-
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
|
|
2922
|
+
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]] = None,
|
|
2915
2923
|
**kwargs) -> ScrapeResponse[Any]:
|
|
2916
2924
|
"""
|
|
2917
2925
|
Scrape a single URL asynchronously.
|
|
@@ -2932,7 +2940,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
|
|
|
2932
2940
|
proxy (Optional[Literal["basic", "stealth", "auto"]]): Proxy type (basic/stealth)
|
|
2933
2941
|
extract (Optional[JsonConfig]): Content extraction settings
|
|
2934
2942
|
json_options (Optional[JsonConfig]): JSON extraction settings
|
|
2935
|
-
actions (Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]]): Actions to perform
|
|
2943
|
+
actions (Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]]): Actions to perform
|
|
2936
2944
|
**kwargs: Additional parameters to pass to the API
|
|
2937
2945
|
|
|
2938
2946
|
Returns:
|
|
@@ -3042,7 +3050,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
|
|
|
3042
3050
|
proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
|
|
3043
3051
|
extract: Optional[JsonConfig] = None,
|
|
3044
3052
|
json_options: Optional[JsonConfig] = None,
|
|
3045
|
-
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
|
|
3053
|
+
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]] = None,
|
|
3046
3054
|
agent: Optional[AgentOptions] = None,
|
|
3047
3055
|
poll_interval: Optional[int] = 2,
|
|
3048
3056
|
idempotency_key: Optional[str] = None,
|
|
@@ -3181,7 +3189,7 @@ class AsyncFirecrawlApp(FirecrawlApp):
|
|
|
3181
3189
|
proxy: Optional[Literal["basic", "stealth", "auto"]] = None,
|
|
3182
3190
|
extract: Optional[JsonConfig] = None,
|
|
3183
3191
|
json_options: Optional[JsonConfig] = None,
|
|
3184
|
-
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
|
|
3192
|
+
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction, PDFAction]]] = None,
|
|
3185
3193
|
agent: Optional[AgentOptions] = None,
|
|
3186
3194
|
idempotency_key: Optional[str] = None,
|
|
3187
3195
|
**kwargs
|
|
@@ -1,12 +1,12 @@
|
|
|
1
|
-
firecrawl/__init__.py,sha256=
|
|
2
|
-
firecrawl/firecrawl.py,sha256=
|
|
1
|
+
firecrawl/__init__.py,sha256=uHnpcSPL_UX_PvPYv7sphq_21zQmzqYILej7FZnMEO4,2613
|
|
2
|
+
firecrawl/firecrawl.py,sha256=2fzg1wKvbH6_KYnEhwPaGv6hYMmW1f9o0mSoCRv0PHw,194334
|
|
3
3
|
firecrawl/__tests__/e2e_withAuth/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
4
4
|
firecrawl/__tests__/e2e_withAuth/test.py,sha256=-Fq2vPcMo0iQi4dwsUkkCd931ybDaTxMBnZbRfGdDcA,7931
|
|
5
5
|
firecrawl/__tests__/v1/e2e_withAuth/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
6
6
|
firecrawl/__tests__/v1/e2e_withAuth/test.py,sha256=k9IsEbdTHL9Cu49M4FpnQDEo2rnG6RqwmZAsK_EVJr4,21069
|
|
7
7
|
tests/test_change_tracking.py,sha256=_IJ5ShLcoj2fHDBaw-nE4I4lHdmDB617ocK_XMHhXps,4177
|
|
8
|
-
firecrawl-2.
|
|
9
|
-
firecrawl-2.
|
|
10
|
-
firecrawl-2.
|
|
11
|
-
firecrawl-2.
|
|
12
|
-
firecrawl-2.
|
|
8
|
+
firecrawl-2.11.0.dist-info/LICENSE,sha256=nPCunEDwjRGHlmjvsiDUyIWbkqqyj3Ej84ntnh0g0zA,1084
|
|
9
|
+
firecrawl-2.11.0.dist-info/METADATA,sha256=Ukyy5PHWLtVjdiwjyRLWxuAy9VLqRwjEjc4iOdTeWro,7166
|
|
10
|
+
firecrawl-2.11.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
|
|
11
|
+
firecrawl-2.11.0.dist-info/top_level.txt,sha256=8T3jOaSN5mtLghO-R3MQ8KO290gIX8hmfxQmglBPdLE,16
|
|
12
|
+
firecrawl-2.11.0.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|