thordata-sdk 1.5.0__py3-none-any.whl → 1.7.0__py3-none-any.whl

thordata/tools/ecommerce.py

@@ -12,9 +12,10 @@ from .base import ToolRequest
 class Amazon:
     """Namespace for Amazon tools."""
 
+    # --- Product Details (5 methods) ---
     @dataclass
-    class Product(ToolRequest):
-        """Amazon Product Details Scraper"""
+    class ProductByAsin(ToolRequest):
+        """Amazon Product Details Scraper by ASIN."""
 
         SPIDER_ID = "amazon_product_by-asin"
         SPIDER_NAME = "amazon.com"
@@ -22,16 +23,112 @@ class Amazon:
         asin: str
         domain: str = "amazon.com"
 
+    # Backward compatible alias
+    Product = ProductByAsin
+
     @dataclass
-    class GlobalProduct(ToolRequest):
-        """Amazon Global Product Details Scraper"""
+    class ProductByUrl(ToolRequest):
+        """Amazon Product Details Scraper by URL."""
 
-        SPIDER_ID = "amazon_global-product_by-url"
+        SPIDER_ID = "amazon_product_by-url"
         SPIDER_NAME = "amazon.com"
 
         url: str
         zip_code: str | None = None
 
+    @dataclass
+    class ProductByKeywords(ToolRequest):
+        """Amazon Product Details Scraper by Keywords."""
+
+        SPIDER_ID = "amazon_product_by-keywords"
+        SPIDER_NAME = "amazon.com"
+
+        keyword: str
+        page_turning: int | None = None
+        lowest_price: float | None = None
+        highest_price: float | None = None
+
+    @dataclass
+    class ProductByCategoryUrl(ToolRequest):
+        """Amazon Product Details Scraper by Category URL."""
+
+        SPIDER_ID = "amazon_product_by-category-url"
+        SPIDER_NAME = "amazon.com"
+
+        url: str
+        sort_by: str | None = None
+        page_turning: int | None = None
+
+    @dataclass
+    class ProductByBestSellers(ToolRequest):
+        """Amazon Product Details Scraper by Best Sellers URL."""
+
+        SPIDER_ID = "amazon_product_by-best-sellers"
+        SPIDER_NAME = "amazon.com"
+
+        url: str
+        page_turning: int | None = None
+
+    # --- Other Amazon Tools ---
+
+    @dataclass
+    class GlobalProductByUrl(ToolRequest):
+        """Amazon Global Product Details Scraper by URL"""
+
+        SPIDER_ID = "amazon_global-product_by-url"
+        SPIDER_NAME = "amazon.com"
+
+        url: str
+
+    # Backward compatible alias
+    GlobalProduct = GlobalProductByUrl
+
+    @dataclass
+    class GlobalProductByCategoryUrl(ToolRequest):
+        """Amazon Global Product Details Scraper by Category URL"""
+
+        SPIDER_ID = "amazon_global-product_by-category-url"
+        SPIDER_NAME = "amazon.com"
+
+        url: str
+        sort_by: str | None = None
+        get_sponsored: str | None = None
+        maximum: int | None = None
+
+    @dataclass
+    class GlobalProductBySellerUrl(ToolRequest):
+        """Amazon Global Product Details Scraper by Seller URL"""
+
+        SPIDER_ID = "amazon_global-product_by-seller-url"
+        SPIDER_NAME = "amazon.com"
+
+        url: str
+        maximum: int | None = None
+
+    @dataclass
+    class GlobalProductByKeywords(ToolRequest):
+        """Amazon Global Product Details Scraper by Keywords"""
+
+        SPIDER_ID = "amazon_global-product_by-keywords"
+        SPIDER_NAME = "amazon.com"
+
+        keyword: str
+        domain: str = "https://www.amazon.com"
+        lowest_price: str | None = None
+        highest_price: str | None = None
+        page_turning: int | None = None
+
+    @dataclass
+    class GlobalProductByKeywordsBrand(ToolRequest):
+        """Amazon Global Product Details Scraper by Keywords and Brand"""
+
+        SPIDER_ID = "amazon_global-product_by-keywords-brand"
+        SPIDER_NAME = "amazon.com"
+
+        keyword: str
+        brands: str
+        page_turning: int | None = None
+
     @dataclass
     class Review(ToolRequest):
         """Amazon Product Review Scraper"""
@@ -59,9 +156,96 @@ class Amazon:
         SPIDER_NAME = "amazon.com"
 
         keyword: str
-        domain: str = "amazon.com"
+        domain: str = "https://www.amazon.com/"
         page_turning: int = 1
-        sort_by: str | None = None  # Best Sellers, Newest Arrivals, etc.
-        min_price: float | None = None
-        max_price: float | None = None
-        get_sponsored: bool | None = None
+
+
+class eBay:
+    """Namespace for eBay tools."""
+
+    @dataclass
+    class ProductByUrl(ToolRequest):
+        """eBay Information Scraper by URL"""
+
+        SPIDER_ID = "ebay_ebay_by-url"
+        SPIDER_NAME = "ebay.com"
+        url: str
+
+    @dataclass
+    class ProductByCategoryUrl(ToolRequest):
+        """eBay Information Scraper by Category URL"""
+
+        SPIDER_ID = "ebay_ebay_by-category-url"
+        SPIDER_NAME = "ebay.com"
+        url: str
+        count: str | None = None
+
+    @dataclass
+    class ProductByKeywords(ToolRequest):
+        """eBay Information Scraper by Keywords"""
+
+        SPIDER_ID = "ebay_ebay_by-keywords"
+        SPIDER_NAME = "ebay.com"
+        keywords: str
+        count: str | None = None
+
+    @dataclass
+    class ProductByListUrl(ToolRequest):
+        """eBay Information Scraper by List URL"""
+
+        SPIDER_ID = "ebay_ebay_by-listurl"
+        SPIDER_NAME = "ebay.com"
+        url: str
+        count: str | None = None
+
+
+class Walmart:
+    """Namespace for Walmart tools."""
+
+    @dataclass
+    class ProductByUrl(ToolRequest):
+        """Walmart Product Information Scraper by URL"""
+
+        SPIDER_ID = "walmart_product_by-url"
+        SPIDER_NAME = "walmart.com"
+        url: str
+        all_variations: str | None = None
+
+    @dataclass
+    class ProductByCategoryUrl(ToolRequest):
+        """Walmart Product Information Scraper by Category URL"""
+
+        SPIDER_ID = "walmart_product_by-category-url"
+        SPIDER_NAME = "walmart.com"
+        category_url: str
+        all_variations: str | None = None
+        page_turning: int | None = None
+
+    @dataclass
+    class ProductBySku(ToolRequest):
+        """Walmart Product Information Scraper by SKU"""
+
+        SPIDER_ID = "walmart_product_by-sku"
+        SPIDER_NAME = "walmart.com"
+        sku: str
+        all_variations: str | None = None
+
+    @dataclass
+    class ProductByKeywords(ToolRequest):
+        """Walmart Product Information Scraper by Keywords"""
+
+        SPIDER_ID = "walmart_product_by-keywords"
+        SPIDER_NAME = "walmart.com"
+        keyword: str
+        domain: str = "https://www.walmart.com/"
+        all_variations: str | None = None
+        page_turning: int | None = None
+
+    @dataclass
+    class ProductByZipcodes(ToolRequest):
+        """Walmart Product Information Scraper by Zipcodes"""
+
+        SPIDER_ID = "walmart_product_by-zipcodes"
+        SPIDER_NAME = "walmart.com"
+        url: str
+        zip_code: str | None = None

thordata/tools/professional.py

@@ -0,0 +1,155 @@
+"""
+Professional Platform Scraper Tools (Indeed, Glassdoor, Crunchbase, etc.)
+"""
+
+from __future__ import annotations
+
+from dataclasses import dataclass
+
+from .base import ToolRequest
+
+
+class Indeed:
+    """Namespace for Indeed tools."""
+
+    @dataclass
+    class JobByUrl(ToolRequest):
+        """Indeed Job Listings Scraper by Job URL"""
+
+        SPIDER_ID = "indeed_job-listings_by-job-url"
+        SPIDER_NAME = "indeed.com"
+        job_url: str
+
+    @dataclass
+    class JobByKeyword(ToolRequest):
+        """Indeed Job Listings Scraper by Keyword"""
+
+        SPIDER_ID = "indeed_job-listings_by-keyword"
+        SPIDER_NAME = "indeed.com"
+        keyword: str
+        location: str
+        country: str | None = None
+        domain: str | None = None
+        date_posted: str | None = None
+        posted_by: str | None = None
+        pay: str | None = None
+        location_radius: str | None = None
+
+    @dataclass
+    class CompanyByListUrl(ToolRequest):
+        """Indeed Companies Info Scraper by Company List URL"""
+
+        SPIDER_ID = "indeed_companies-info_by-company-list-url"
+        SPIDER_NAME = "indeed.com"
+        company_list_url: str
+
+    @dataclass
+    class CompanyByKeyword(ToolRequest):
+        """Indeed Companies Info Scraper by Keyword"""
+
+        SPIDER_ID = "indeed_companies-info_by-keyword"
+        SPIDER_NAME = "indeed.com"
+        keyword: str
+
+    @dataclass
+    class CompanyByIndustryAndState(ToolRequest):
+        """Indeed Companies Info Scraper by Industry and State"""
+
+        SPIDER_ID = "indeed_companies-info_by-industry-and-state"
+        SPIDER_NAME = "indeed.com"
+        industry: str
+        state: str | None = None
+
+    @dataclass
+    class CompanyByUrl(ToolRequest):
+        """Indeed Companies Info Scraper by Company URL"""
+
+        SPIDER_ID = "indeed_companies-info_by-company-url"
+        SPIDER_NAME = "indeed.com"
+        company_url: str
+
+
+class Glassdoor:
+    """Namespace for Glassdoor tools."""
+
+    @dataclass
+    class CompanyByUrl(ToolRequest):
+        """Glassdoor Company Overview Information Scraper by URL"""
+
+        SPIDER_ID = "glassdoor_company_by-url"
+        SPIDER_NAME = "glassdoor.com"
+        url: str
+
+    @dataclass
+    class CompanyByInputFilter(ToolRequest):
+        """Glassdoor Company Overview Information Scraper by Input Filter"""
+
+        SPIDER_ID = "glassdoor_company_by-inputfilter"
+        SPIDER_NAME = "glassdoor.com"
+        company_name: str
+        location: str | None = None
+        industries: str | None = None
+        Job_title: str | None = None  # Note: capital J in API
+
+    @dataclass
+    class CompanyByKeywords(ToolRequest):
+        """Glassdoor Company Overview Information Scraper by Keywords"""
+
+        SPIDER_ID = "glassdoor_company_by-keywords"
+        SPIDER_NAME = "glassdoor.com"
+        search_url: str
+        max_search_results: int | None = None
+
+    @dataclass
+    class CompanyByListUrl(ToolRequest):
+        """Glassdoor Company Overview Information Scraper by List URL"""
+
+        SPIDER_ID = "glassdoor_company_by-listurl"
+        SPIDER_NAME = "glassdoor.com"
+        url: str
+
+    @dataclass
+    class JobByUrl(ToolRequest):
+        """Glassdoor Job Information Scraper by URL"""
+
+        SPIDER_ID = "glassdoor_joblistings_by-url"
+        SPIDER_NAME = "glassdoor.com"
+        url: str
+
+    @dataclass
+    class JobByKeywords(ToolRequest):
+        """Glassdoor Job Information Scraper by Keywords"""
+
+        SPIDER_ID = "glassdoor_joblistings_by-keywords"
+        SPIDER_NAME = "glassdoor.com"
+        keyword: str
+        location: str
+        country: str | None = None
+
+    @dataclass
+    class JobByListUrl(ToolRequest):
+        """Glassdoor Job Information Scraper by List URL"""
+
+        SPIDER_ID = "glassdoor_joblistings_by-listurl"
+        SPIDER_NAME = "glassdoor.com"
+        url: str
+
+
+class Crunchbase:
+    """Namespace for Crunchbase tools."""
+
+    @dataclass
+    class CompanyByUrl(ToolRequest):
+        """Crunchbase Company Information Scraper by URL"""
+
+        SPIDER_ID = "crunchbase_company_by-url"
+        SPIDER_NAME = "crunchbase.com"
+        url: str
+
+    @dataclass
+    class CompanyByKeywords(ToolRequest):
+        """Crunchbase Company Information Scraper by Keywords"""
+
+        SPIDER_ID = "crunchbase_company_by-keywords"
+        SPIDER_NAME = "crunchbase.com"
+        keyword: str

thordata/tools/search.py

@@ -13,13 +13,47 @@ class GoogleMaps:
     """Namespace for Google Maps tools."""
 
     @dataclass
-    class Details(ToolRequest):
-        """Google Maps Details Information Scraper"""
+    class DetailsByUrl(ToolRequest):
+        """Google Maps Details Scraper by URL."""
 
         SPIDER_ID = "google_map-details_by-url"
         SPIDER_NAME = "google.com"
 
-        url: str  # Google Maps URL
+        url: str
+
+    @dataclass
+    class DetailsByCid(ToolRequest):
+        """Google Maps Details Scraper by CID."""
+
+        SPIDER_ID = "google_map-details_by-cid"
+        SPIDER_NAME = "google.com"
+
+        CID: str
+
+    @dataclass
+    class DetailsByLocation(ToolRequest):
+        """Google Maps Details Scraper by Location keyword + country (+ optional lat/long/zoom)."""  # noqa: E501
+
+        SPIDER_ID = "google_map-details_by-location"
+        SPIDER_NAME = "google.com"
+
+        country: str
+        keyword: str
+        lat: str | None = None
+        long: str | None = None
+        zoom_level: str | None = None
+
+    @dataclass
+    class DetailsByPlaceId(ToolRequest):
+        """Google Maps Details Scraper by Place ID."""
+
+        SPIDER_ID = "google_map-details_by-placeid"
+        SPIDER_NAME = "google.com"
+
+        place_id: str
+
+    # Backward compatible alias: keep old name working
+    Details = DetailsByUrl
 
     @dataclass
     class Reviews(ToolRequest):
@@ -37,14 +71,22 @@ class GoogleShopping:
 
     @dataclass
     class Product(ToolRequest):
-        """Google Shopping Information Scraper"""
+        """Google Shopping Information Scraper by URL"""
 
         SPIDER_ID = "google_shopping_by-url"
         SPIDER_NAME = "google.com"
-
         url: str
         country: str | None = None  # e.g. "US"
 
+    @dataclass
+    class ProductByKeywords(ToolRequest):
+        """Google Shopping Information Scraper by Keywords"""
+
+        SPIDER_ID = "google_shopping_by-keywords"
+        SPIDER_NAME = "google.com"
+        keyword: str
+        country: str | None = None  # e.g. "US"
+
 
 class GooglePlay:
     """Namespace for Google Play Store tools."""