AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-06-04 11:24:40 +08:00
Code Issues Packages Projects Releases Wiki Activity

Nick: (#1506)

Browse Source
This commit is contained in:
Nicolas 2025-04-29 11:06:35 -03:00 committed by GitHub
parent 8053a7cedd
commit a0a1675829
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 15 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
apps/python-sdk/firecrawl/__init__.py
View File

@ -11,9 +11,9 @@ For more information visit https://github.com/firecrawl/
import logging
import os
from .firecrawl import FirecrawlApp, JsonConfig, ScrapeOptions # noqa
from .firecrawl import FirecrawlApp, JsonConfig, ScrapeOptions, ChangeTrackingOptions # noqa
__version__ = "2.4.3"
__version__ = "2.5.0"
# Define the logger for the Firecrawl project
logger: logging.Logger = logging.getLogger("firecrawl")

14
apps/python-sdk/firecrawl/firecrawl.py
View File

@ -135,6 +135,12 @@ class WebhookConfig(pydantic.BaseModel):
metadata: Optional[Dict[str, str]] = None
events: Optional[List[Literal["completed", "failed", "page", "started"]]] = None
class ChangeTrackingOptions(pydantic.BaseModel):
"""Configuration for change tracking."""
modes: Optional[List[Literal["git-diff", "json"]]] = None
schema: Optional[Any] = None
prompt: Optional[str] = None
class ScrapeOptions(pydantic.BaseModel):
"""Parameters for scraping operations."""
formats: Optional[List[Literal["markdown", "html", "rawHtml", "content", "links", "screenshot", "screenshot@fullPage", "extract", "json", "changeTracking"]]] = None
@ -150,6 +156,7 @@ class ScrapeOptions(pydantic.BaseModel):
removeBase64Images: Optional[bool] = None
blockAds: Optional[bool] = None
proxy: Optional[Literal["basic", "stealth"]] = None
changeTrackingOptions: Optional[ChangeTrackingOptions] = None
class WaitAction(pydantic.BaseModel):
"""Wait action to perform during scraping."""
@ -454,6 +461,7 @@ class FirecrawlApp:
extract: Optional[JsonConfig] = None,
json_options: Optional[JsonConfig] = None,
actions: Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]] = None,
change_tracking_options: Optional[ChangeTrackingOptions] = None,
**kwargs) -> ScrapeResponse[Any]:
"""
Scrape and extract content from a URL.
@ -475,6 +483,7 @@ class FirecrawlApp:
extract (Optional[JsonConfig]): Content extraction settings
json_options (Optional[JsonConfig]): JSON extraction settings
actions (Optional[List[Union[WaitAction, ScreenshotAction, ClickAction, WriteAction, PressAction, ScrollAction, ScrapeAction, ExecuteJavascriptAction]]]): Actions to perform
change_tracking_options (Optional[ChangeTrackingOptions]): Change tracking settings
Returns:
@ -530,6 +539,9 @@ class FirecrawlApp:
scrape_params['jsonOptions'] = json_options.dict(exclude_none=True)
if actions:
scrape_params['actions'] = [action.dict(exclude_none=True) for action in actions]
if change_tracking_options:
scrape_params['changeTrackingOptions'] = change_tracking_options.dict(exclude_none=True)
scrape_params.update(kwargs)
# Make request
@ -2424,7 +2436,7 @@ class FirecrawlApp:
method_params = {
"scrape_url": {"formats", "include_tags", "exclude_tags", "only_main_content", "wait_for",
"timeout", "location", "mobile", "skip_tls_verification", "remove_base64_images",
"block_ads", "proxy", "extract", "json_options", "actions"},
"block_ads", "proxy", "extract", "json_options", "actions", "change_tracking_options"},
"search": {"limit", "tbs", "filter", "lang", "country", "location", "timeout", "scrape_options"},
"crawl_url": {"include_paths", "exclude_paths", "max_depth", "max_discovery_depth", "limit",
"allow_backward_links", "allow_external_links", "ignore_sitemap", "scrape_options",