feat(scrape): add Yelp search parser

Merge pull request #2306 from context-dot-dev/feat/yelp-search-parser

Stainless-Generated-From: 163fdec2b765044684ae40e57cd7342cb7548a41

Author: stlc-bot

src/context/dev/types/batch_get_results_response.py

@@ -294,7 +294,7 @@ class DataOkResultMetadata(BaseModel):
 
 class DataOkResultParsed(BaseModel):
     """
-    Custom rules return fields after content filters; unmatched fields are null ([] for lists). The google-maps parser returns business records in data.results, google-maps-reviews returns data.reviews, and the google-play parser returns one app record as data, google-play-reviews returns data.reviews, app-store and app-store-reviews do the same for the App Store, g2-reviews returns data.reviews for a G2 product, instagram-profile and instagram-post return one record as data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return one record as data, tiktok-feed returns data.videos, tiktok-comments returns data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return data.users, emails, phone-numbers, and links return data.emails, data.phone_numbers, and data.links from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read their data directly, independently of DOM filters and other outputs.
+    Custom rules return fields after content filters; unmatched fields are null ([] for lists). The google-maps parser returns business records in data.results, google-maps-reviews returns data.reviews, and the google-play parser returns one app record as data, google-play-reviews returns data.reviews, app-store and app-store-reviews do the same for the App Store, g2-reviews returns data.reviews for a G2 product, instagram-profile and instagram-post return one record as data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return one record as data, tiktok-feed returns data.videos, tiktok-comments returns data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return data.users, yelp-search returns up to 20 ranked organic businesses in data.businesses, plus total and pagination, from a Yelp search URL; emails, phone-numbers, and links return data.emails, data.phone_numbers, and data.links from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read their data directly, independently of DOM filters and other outputs.
     """
 
     data: Optional[Dict[str, object]] = None
@@ -323,6 +323,7 @@ class DataOkResultParsed(BaseModel):
         "tiktok-followers",
         "tiktok-following",
         "tiktok-user-search",
+        "yelp-search",
         "emails",
         "phone-numbers",
         "links",
@@ -522,10 +523,11 @@ class DataOkResult(BaseModel):
     data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return
     one record as data, tiktok-feed returns data.videos, tiktok-comments returns
     data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return
-    data.users, emails, phone-numbers, and links return data.emails,
-    data.phone_numbers, and data.links from the rendered page; the store, Maps, G2,
-    Instagram, and TikTok parsers read their data directly, independently of DOM
-    filters and other outputs.
+    data.users, yelp-search returns up to 20 ranked organic businesses in
+    data.businesses, plus total and pagination, from a Yelp search URL; emails,
+    phone-numbers, and links return data.emails, data.phone_numbers, and data.links
+    from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read
+    their data directly, independently of DOM filters and other outputs.
     """
 
     product: DataOkResultProduct
@@ -827,7 +829,7 @@ class DataErrorResultMetadata(BaseModel):
 
 class DataErrorResultParsed(BaseModel):
     """
-    Custom rules return fields after content filters; unmatched fields are null ([] for lists). The google-maps parser returns business records in data.results, google-maps-reviews returns data.reviews, and the google-play parser returns one app record as data, google-play-reviews returns data.reviews, app-store and app-store-reviews do the same for the App Store, g2-reviews returns data.reviews for a G2 product, instagram-profile and instagram-post return one record as data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return one record as data, tiktok-feed returns data.videos, tiktok-comments returns data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return data.users, emails, phone-numbers, and links return data.emails, data.phone_numbers, and data.links from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read their data directly, independently of DOM filters and other outputs.
+    Custom rules return fields after content filters; unmatched fields are null ([] for lists). The google-maps parser returns business records in data.results, google-maps-reviews returns data.reviews, and the google-play parser returns one app record as data, google-play-reviews returns data.reviews, app-store and app-store-reviews do the same for the App Store, g2-reviews returns data.reviews for a G2 product, instagram-profile and instagram-post return one record as data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return one record as data, tiktok-feed returns data.videos, tiktok-comments returns data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return data.users, yelp-search returns up to 20 ranked organic businesses in data.businesses, plus total and pagination, from a Yelp search URL; emails, phone-numbers, and links return data.emails, data.phone_numbers, and data.links from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read their data directly, independently of DOM filters and other outputs.
     """
 
     data: Optional[Dict[str, object]] = None
@@ -856,6 +858,7 @@ class DataErrorResultParsed(BaseModel):
         "tiktok-followers",
         "tiktok-following",
         "tiktok-user-search",
+        "yelp-search",
         "emails",
         "phone-numbers",
         "links",
@@ -1056,10 +1059,11 @@ class DataErrorResult(BaseModel):
     data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return
     one record as data, tiktok-feed returns data.videos, tiktok-comments returns
     data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return
-    data.users, emails, phone-numbers, and links return data.emails,
-    data.phone_numbers, and data.links from the rendered page; the store, Maps, G2,
-    Instagram, and TikTok parsers read their data directly, independently of DOM
-    filters and other outputs.
+    data.users, yelp-search returns up to 20 ranked organic businesses in
+    data.businesses, plus total and pagination, from a Yelp search URL; emails,
+    phone-numbers, and links return data.emails, data.phone_numbers, and data.links
+    from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read
+    their data directly, independently of DOM filters and other outputs.
     """
 
     product: DataErrorResultProduct

src/context/dev/types/batch_submit_params.py

@@ -894,6 +894,7 @@ class InputScrapeDataBatchUnifiedScrapeDataParseParamsPrebuiltParser(TypedDict,
             "tiktok-followers",
             "tiktok-following",
             "tiktok-user-search",
+            "yelp-search",
             "emails",
             "phone-numbers",
             "links",
@@ -958,17 +959,19 @@ class InputScrapeDataBatchUnifiedScrapeDataParseParamsPrebuiltParser(TypedDict,
     (/search/user?q={query}) as data.users: id, username, nickname, biography,
     avatar_url, sec_uid, follower_count, like_count, and is_verified. The TikTok
     parsers accept tiktok.com, www.tiktok.com, and m.tiktok.com URLs but not short
-    links (vm.tiktok.com, vt.tiktok.com, tiktok.com/t/…). emails accepts any page
-    and returns its email addresses as data.emails ([{ email }]), read from mailto
-    links, Cloudflare-protected addresses, and visible text. phone-numbers accepts
-    any page and returns its valid phone numbers in E.164 as data.phone_numbers ([{
-    phone }]), read from tel links and visible text; numbers without a country code
-    are read for the country of the site TLD, defaulting to US. links accepts any
-    page and returns its unique http(s) links as data.links ([{ url, text }]), with
-    absolute URLs; text falls back to aria-label or image alt and is null when a
-    link has none. The emails parser reads the rendered page and respects content
-    filters; the other prebuilt parsers read their data independently of DOM
-    filters.
+    links (vm.tiktok.com, vt.tiktok.com, tiktok.com/t/…). yelp-search accepts Yelp
+    search URLs with find_desc and find_loc, reads start as the result offset, and
+    returns up to 20 ranked organic businesses in data.businesses with total and
+    pagination. emails accepts any page and returns its email addresses as
+    data.emails ([{ email }]), read from mailto links, Cloudflare-protected
+    addresses, and visible text. phone-numbers accepts any page and returns its
+    valid phone numbers in E.164 as data.phone_numbers ([{ phone }]), read from tel
+    links and visible text; numbers without a country code are read for the country
+    of the site TLD, defaulting to US. links accepts any page and returns its unique
+    http(s) links as data.links ([{ url, text }]), with absolute URLs; text falls
+    back to aria-label or image alt and is null when a link has none. The emails
+    parser reads the rendered page and respects content filters; the other prebuilt
+    parsers read their data independently of DOM filters.
     """
 
     type: Required[Literal["prebuilt"]]
@@ -2534,6 +2537,7 @@ class InputCrawlDataBatchUnifiedCrawlDataParseParamsPrebuiltParser(TypedDict, to
             "tiktok-followers",
             "tiktok-following",
             "tiktok-user-search",
+            "yelp-search",
             "emails",
             "phone-numbers",
             "links",
@@ -2598,17 +2602,19 @@ class InputCrawlDataBatchUnifiedCrawlDataParseParamsPrebuiltParser(TypedDict, to
     (/search/user?q={query}) as data.users: id, username, nickname, biography,
     avatar_url, sec_uid, follower_count, like_count, and is_verified. The TikTok
     parsers accept tiktok.com, www.tiktok.com, and m.tiktok.com URLs but not short
-    links (vm.tiktok.com, vt.tiktok.com, tiktok.com/t/…). emails accepts any page
-    and returns its email addresses as data.emails ([{ email }]), read from mailto
-    links, Cloudflare-protected addresses, and visible text. phone-numbers accepts
-    any page and returns its valid phone numbers in E.164 as data.phone_numbers ([{
-    phone }]), read from tel links and visible text; numbers without a country code
-    are read for the country of the site TLD, defaulting to US. links accepts any
-    page and returns its unique http(s) links as data.links ([{ url, text }]), with
-    absolute URLs; text falls back to aria-label or image alt and is null when a
-    link has none. The emails parser reads the rendered page and respects content
-    filters; the other prebuilt parsers read their data independently of DOM
-    filters.
+    links (vm.tiktok.com, vt.tiktok.com, tiktok.com/t/…). yelp-search accepts Yelp
+    search URLs with find_desc and find_loc, reads start as the result offset, and
+    returns up to 20 ranked organic businesses in data.businesses with total and
+    pagination. emails accepts any page and returns its email addresses as
+    data.emails ([{ email }]), read from mailto links, Cloudflare-protected
+    addresses, and visible text. phone-numbers accepts any page and returns its
+    valid phone numbers in E.164 as data.phone_numbers ([{ phone }]), read from tel
+    links and visible text; numbers without a country code are read for the country
+    of the site TLD, defaulting to US. links accepts any page and returns its unique
+    http(s) links as data.links ([{ url, text }]), with absolute URLs; text falls
+    back to aria-label or image alt and is null when a link has none. The emails
+    parser reads the rendered page and respects content filters; the other prebuilt
+    parsers read their data independently of DOM filters.
     """
 
     type: Required[Literal["prebuilt"]]

src/context/dev/types/web_scrape_params.py

@@ -231,6 +231,7 @@ class ParseParamsPrebuiltParser(TypedDict, total=False):
             "tiktok-followers",
             "tiktok-following",
             "tiktok-user-search",
+            "yelp-search",
             "emails",
             "phone-numbers",
             "links",
@@ -295,17 +296,19 @@ class ParseParamsPrebuiltParser(TypedDict, total=False):
     (/search/user?q={query}) as data.users: id, username, nickname, biography,
     avatar_url, sec_uid, follower_count, like_count, and is_verified. The TikTok
     parsers accept tiktok.com, www.tiktok.com, and m.tiktok.com URLs but not short
-    links (vm.tiktok.com, vt.tiktok.com, tiktok.com/t/…). emails accepts any page
-    and returns its email addresses as data.emails ([{ email }]), read from mailto
-    links, Cloudflare-protected addresses, and visible text. phone-numbers accepts
-    any page and returns its valid phone numbers in E.164 as data.phone_numbers ([{
-    phone }]), read from tel links and visible text; numbers without a country code
-    are read for the country of the site TLD, defaulting to US. links accepts any
-    page and returns its unique http(s) links as data.links ([{ url, text }]), with
-    absolute URLs; text falls back to aria-label or image alt and is null when a
-    link has none. The emails parser reads the rendered page and respects content
-    filters; the other prebuilt parsers read their data independently of DOM
-    filters.
+    links (vm.tiktok.com, vt.tiktok.com, tiktok.com/t/…). yelp-search accepts Yelp
+    search URLs with find_desc and find_loc, reads start as the result offset, and
+    returns up to 20 ranked organic businesses in data.businesses with total and
+    pagination. emails accepts any page and returns its email addresses as
+    data.emails ([{ email }]), read from mailto links, Cloudflare-protected
+    addresses, and visible text. phone-numbers accepts any page and returns its
+    valid phone numbers in E.164 as data.phone_numbers ([{ phone }]), read from tel
+    links and visible text; numbers without a country code are read for the country
+    of the site TLD, defaulting to US. links accepts any page and returns its unique
+    http(s) links as data.links ([{ url, text }]), with absolute URLs; text falls
+    back to aria-label or image alt and is null when a link has none. The emails
+    parser reads the rendered page and respects content filters; the other prebuilt
+    parsers read their data independently of DOM filters.
     """
 
     type: Required[Literal["prebuilt"]]

src/context/dev/types/web_scrape_response.py

@@ -267,7 +267,7 @@ class Metadata(BaseModel):
 
 class Parsed(BaseModel):
     """
-    Custom rules return fields after content filters; unmatched fields are null ([] for lists). The google-maps parser returns business records in data.results, google-maps-reviews returns data.reviews, and the google-play parser returns one app record as data, google-play-reviews returns data.reviews, app-store and app-store-reviews do the same for the App Store, g2-reviews returns data.reviews for a G2 product, instagram-profile and instagram-post return one record as data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return one record as data, tiktok-feed returns data.videos, tiktok-comments returns data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return data.users, emails, phone-numbers, and links return data.emails, data.phone_numbers, and data.links from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read their data directly, independently of DOM filters and other outputs.
+    Custom rules return fields after content filters; unmatched fields are null ([] for lists). The google-maps parser returns business records in data.results, google-maps-reviews returns data.reviews, and the google-play parser returns one app record as data, google-play-reviews returns data.reviews, app-store and app-store-reviews do the same for the App Store, g2-reviews returns data.reviews for a G2 product, instagram-profile and instagram-post return one record as data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return one record as data, tiktok-feed returns data.videos, tiktok-comments returns data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return data.users, yelp-search returns up to 20 ranked organic businesses in data.businesses, plus total and pagination, from a Yelp search URL; emails, phone-numbers, and links return data.emails, data.phone_numbers, and data.links from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read their data directly, independently of DOM filters and other outputs.
     """
 
     data: Optional[Dict[str, object]] = None
@@ -296,6 +296,7 @@ class Parsed(BaseModel):
         "tiktok-followers",
         "tiktok-following",
         "tiktok-user-search",
+        "yelp-search",
         "emails",
         "phone-numbers",
         "links",
@@ -491,10 +492,11 @@ class WebScrapeResponse(BaseModel):
     data, instagram-feed returns data.posts, tiktok-profile and tiktok-video return
     one record as data, tiktok-feed returns data.videos, tiktok-comments returns
     data.comments, tiktok-followers, tiktok-following, and tiktok-user-search return
-    data.users, emails, phone-numbers, and links return data.emails,
-    data.phone_numbers, and data.links from the rendered page; the store, Maps, G2,
-    Instagram, and TikTok parsers read their data directly, independently of DOM
-    filters and other outputs.
+    data.users, yelp-search returns up to 20 ranked organic businesses in
+    data.businesses, plus total and pagination, from a Yelp search URL; emails,
+    phone-numbers, and links return data.emails, data.phone_numbers, and data.links
+    from the rendered page; the store, Maps, G2, Instagram, and TikTok parsers read
+    their data directly, independently of DOM filters and other outputs.
     """
 
     product: Product