CodeCow/Scrapegraph-ai
1
0
Fork 0
mirror of https://github.com/VinciGit00/Scrapegraph-ai.git synced 2026-06-28 21:01:55 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: add integration with scrape.do

Browse Source
This commit is contained in:
Marco Vinciguerra 2024-10-23 12:08:00 +02:00
parent 5002c713d5
commit ae275ec5e8
2 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
scrapegraphai/nodes/fetch_node.py
View File

@ -270,10 +270,10 @@ class FetchNode(BaseNode):
else:
loader_kwargs = {}
if self.node_config is not None:
if self.node_config:
loader_kwargs = self.node_config.get("loader_kwargs", {})
if self.browser_base is not None:
if self.browser_base:
try:
from ..docloaders.browser_base import browser_base_fetch
except ImportError:
@ -285,7 +285,7 @@ class FetchNode(BaseNode):
document = [Document(page_content=content,
metadata={"source": source}) for content in data]
elif self.scrape_do is not None:
elif self.scrape_do:
from ..docloaders.scrape_do import scrape_do_fetch
if (self.scrape_do.get("use_proxy") is None) or \
self.scrape_do.get("geoCode") is None or \

6
scrapegraphai/nodes/fetch_node_level_k.py
View File

@ -57,6 +57,7 @@ class FetchNodeLevelK(BaseNode):
self.headless = node_config.get("headless", True) if node_config else True
self.loader_kwargs = node_config.get("loader_kwargs", {}) if node_config else {}
self.browser_base = node_config.get("browser_base", None)
self.scrape_do = node_config.get("scrape_do", None)
self.depth = node_config.get("depth", 1) if node_config else 1
self.only_inside_links = node_config.get("only_inside_links", False) if node_config else False
self.min_input_len = 1
@ -115,6 +116,11 @@ class FetchNodeLevelK(BaseNode):
self.browser_base.get("project_id"), [source])
document = [Document(page_content=content,
metadata={"source": source}) for content in data]
elif self.scrape_do:
from ..docloaders.scrape_do import scrape_do_fetch
data = scrape_do_fetch(self.scrape_do.get("api_key"), source)
document = [Document(page_content=data,
metadata={"source": source})]
else:
loader = ChromiumLoader([source], headless=self.headless, **loader_kwargs)
document = loader.load()