From b95244a60b461748a59894f06df7f62d84e2730f Mon Sep 17 00:00:00 2001 From: via Date: Tue, 18 Mar 2025 15:40:25 +0800 Subject: [PATCH 1/4] add bing search --- app/tool/search/__init__.py | 2 + app/tool/search/bing_search.py | 153 +++++++++++++++++++++++++++++++++ app/tool/web_search.py | 2 + 3 files changed, 157 insertions(+) create mode 100644 app/tool/search/bing_search.py diff --git a/app/tool/search/__init__.py b/app/tool/search/__init__.py index 4f486ac..8b6cfdb 100644 --- a/app/tool/search/__init__.py +++ b/app/tool/search/__init__.py @@ -2,6 +2,7 @@ from app.tool.search.baidu_search import BaiduSearchEngine from app.tool.search.base import WebSearchEngine from app.tool.search.duckduckgo_search import DuckDuckGoSearchEngine from app.tool.search.google_search import GoogleSearchEngine +from app.tool.search.bing_search import BingSearchEngine __all__ = [ @@ -9,4 +10,5 @@ __all__ = [ "BaiduSearchEngine", "DuckDuckGoSearchEngine", "GoogleSearchEngine", + "BingSearchEngine", ] diff --git a/app/tool/search/bing_search.py b/app/tool/search/bing_search.py new file mode 100644 index 0000000..53e94c9 --- /dev/null +++ b/app/tool/search/bing_search.py @@ -0,0 +1,153 @@ +import asyncio +from typing import List +import requests +from app.logger import logger +from bs4 import BeautifulSoup +from app.tool.search.base import WebSearchEngine + +ABSTRACT_MAX_LENGTH = 300 + +USER_AGENTS = [ + 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36', + 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)', + 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/49.0.2623.108 Chrome/49.0.2623.108 Safari/537.36', + 'Mozilla/5.0 (Windows; U; Windows NT 5.1; pt-BR) AppleWebKit/533.3 (KHTML, like Gecko) QtWeb Internet Browser/3.7 http://www.QtWeb.net', + 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36', + 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) ChromePlus/4.0.222.3 Chrome/4.0.222.3 Safari/532.2', + 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.4pre) Gecko/20070404 K-Ninja/2.1.3', + 'Mozilla/5.0 (Future Star Technologies Corp.; Star-Blade OS; x86_64; U; en-US) iNet Browser 4.7', + 'Mozilla/5.0 (Windows; U; Windows NT 6.1; rv:2.2) Gecko/20110201', + 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.13) Gecko/20080414 Firefox/2.0.0.13 Pogo/2.0.0.13.6866' +] + +HEADERS = { + "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8", + "Content-Type": "application/x-www-form-urlencoded", + "User-Agent": USER_AGENTS[0], + "Referer": "https://www.bing.com/", + "Accept-Encoding": "gzip, deflate", + "Accept-Language": "zh-CN,zh;q=0.9" +} + +BING_HOST_URL = "https://www.bing.com" +BING_SEARCH_URL = "https://www.bing.com/search?q=" + + +class BingSearchEngine(WebSearchEngine): + session: requests.Session = None + + def __init__(self, **data): + """Initialize the BingSearch tool with a requests session.""" + super().__init__(**data) + self.session = requests.Session() + self.session.headers.update(HEADERS) + + def _search_sync(self, query: str, num_results: int = 10) -> List[str]: + """ + Synchronous Bing search implementation to retrieve a list of URLs matching a query. + + Args: + query (str): The search query to submit to Bing. Must not be empty. + num_results (int, optional): The maximum number of URLs to return. Defaults to 10. + + Returns: + List[str]: A list of URLs from the search results, capped at `num_results`. + Returns an empty list if the query is empty or no results are found. + + Notes: + - Pagination is handled by incrementing the `first` parameter and following `next_url` links. + - If fewer results than `num_results` are available, all found URLs are returned. + """ + if not query: + return [] + + list_result = [] + first = 1 + next_url = BING_SEARCH_URL + query + + while len(list_result) < num_results: + data, next_url = self._parse_html(next_url, rank_start=len(list_result), first=first) + if data: + list_result.extend([item["url"] for item in data]) + if not next_url: + break + first += 10 + + return list_result[:num_results] + + def _parse_html(self, url: str, rank_start: int = 0, first: int = 1) -> tuple: + """ + Parse Bing search result HTML synchronously to extract search results and the next page URL. + + Args: + url (str): The URL of the Bing search results page to parse. + rank_start (int, optional): The starting rank for numbering the search results. Defaults to 0. + first (int, optional): Unused parameter (possibly legacy). Defaults to 1. + Returns: + tuple: A tuple containing: + - list: A list of dictionaries with keys 'title', 'abstract', 'url', and 'rank' for each result. + - str or None: The URL of the next results page, or None if there is no next page. + Example: + This function is called by `execute` in the following way: + ```python + results, next_url = self._parse_html(url, rank_start=0) + ``` + """ + try: + res = self.session.get(url=url) + res.encoding = "utf-8" + root = BeautifulSoup(res.text, "lxml") + + list_data = [] + ol_results = root.find("ol", id="b_results") + if not ol_results: + return [], None + + for li in ol_results.find_all("li", class_="b_algo"): + title = '' + url = '' + abstract = '' + try: + h2 = li.find("h2") + if h2: + title = h2.text.strip() + url = h2.a['href'].strip() + + p = li.find("p") + if p: + abstract = p.text.strip() + + if ABSTRACT_MAX_LENGTH and len(abstract) > ABSTRACT_MAX_LENGTH: + abstract = abstract[:ABSTRACT_MAX_LENGTH] + + rank_start += 1 + list_data.append({"title": title, "abstract": abstract, "url": url, "rank": rank_start}) + except Exception: + continue + + next_btn = root.find("a", title="Next page") + if not next_btn: + return list_data, None + + next_url = BING_HOST_URL + next_btn["href"] + return list_data, next_url + except Exception as e: + logger.warning(f"Error parsing HTML: {e}") + return [], None + + async def execute(self, query: str, num_results: int = 10) -> List[str]: + """ + Execute a Bing search and return a list of URLs asynchronously. + + Args: + query (str): The search query to submit to Bing. + num_results (int, optional): The number of search results to return. Default is 10. + + Returns: + List[str]: A list of URLs matching the search query. + """ + loop = asyncio.get_event_loop() + links = await loop.run_in_executor( + None, lambda: self._search_sync(query, num_results=num_results) + ) + return links diff --git a/app/tool/web_search.py b/app/tool/web_search.py index 7b1018b..99d8916 100644 --- a/app/tool/web_search.py +++ b/app/tool/web_search.py @@ -10,6 +10,7 @@ from app.tool.search import ( DuckDuckGoSearchEngine, GoogleSearchEngine, WebSearchEngine, + BingSearchEngine ) @@ -37,6 +38,7 @@ class WebSearch(BaseTool): "google": GoogleSearchEngine(), "baidu": BaiduSearchEngine(), "duckduckgo": DuckDuckGoSearchEngine(), + "bing": BingSearchEngine() } async def execute(self, query: str, num_results: int = 10) -> List[str]: From b62bf92e19849915cb9ca0d878bd27e3e00281ad Mon Sep 17 00:00:00 2001 From: via Date: Tue, 18 Mar 2025 16:57:29 +0800 Subject: [PATCH 2/4] modified bing search --- app/tool/search/bing_search.py | 29 +++++------------------------ 1 file changed, 5 insertions(+), 24 deletions(-) diff --git a/app/tool/search/bing_search.py b/app/tool/search/bing_search.py index 53e94c9..c5eaa86 100644 --- a/app/tool/search/bing_search.py +++ b/app/tool/search/bing_search.py @@ -1,4 +1,3 @@ -import asyncio from typing import List import requests from app.logger import logger @@ -45,13 +44,13 @@ class BingSearchEngine(WebSearchEngine): def _search_sync(self, query: str, num_results: int = 10) -> List[str]: """ Synchronous Bing search implementation to retrieve a list of URLs matching a query. - + Args: query (str): The search query to submit to Bing. Must not be empty. num_results (int, optional): The maximum number of URLs to return. Defaults to 10. Returns: - List[str]: A list of URLs from the search results, capped at `num_results`. + List[str]: A list of URLs from the search results, capped at `num_results`. Returns an empty list if the query is empty or no results are found. Notes: @@ -87,11 +86,6 @@ class BingSearchEngine(WebSearchEngine): tuple: A tuple containing: - list: A list of dictionaries with keys 'title', 'abstract', 'url', and 'rank' for each result. - str or None: The URL of the next results page, or None if there is no next page. - Example: - This function is called by `execute` in the following way: - ```python - results, next_url = self._parse_html(url, rank_start=0) - ``` """ try: res = self.session.get(url=url) @@ -135,19 +129,6 @@ class BingSearchEngine(WebSearchEngine): logger.warning(f"Error parsing HTML: {e}") return [], None - async def execute(self, query: str, num_results: int = 10) -> List[str]: - """ - Execute a Bing search and return a list of URLs asynchronously. - - Args: - query (str): The search query to submit to Bing. - num_results (int, optional): The number of search results to return. Default is 10. - - Returns: - List[str]: A list of URLs matching the search query. - """ - loop = asyncio.get_event_loop() - links = await loop.run_in_executor( - None, lambda: self._search_sync(query, num_results=num_results) - ) - return links + def perform_search(self, query, num_results=10, *args, **kwargs): + """Bing search engine.""" + return self._search_sync(query, num_results=num_results) \ No newline at end of file From 47adb33bd9352450cb5c070f62c26832d8862207 Mon Sep 17 00:00:00 2001 From: via Date: Wed, 19 Mar 2025 09:13:47 +0800 Subject: [PATCH 3/4] Apply black and isort formatting --- app/tool/search/__init__.py | 3 +-- app/tool/search/bing_search.py | 49 +++++++++++++++++++++------------- app/tool/web_search.py | 8 +++--- 3 files changed, 35 insertions(+), 25 deletions(-) diff --git a/app/tool/search/__init__.py b/app/tool/search/__init__.py index 8b6cfdb..70ea3d7 100644 --- a/app/tool/search/__init__.py +++ b/app/tool/search/__init__.py @@ -1,9 +1,8 @@ from app.tool.search.baidu_search import BaiduSearchEngine from app.tool.search.base import WebSearchEngine +from app.tool.search.bing_search import BingSearchEngine from app.tool.search.duckduckgo_search import DuckDuckGoSearchEngine from app.tool.search.google_search import GoogleSearchEngine -from app.tool.search.bing_search import BingSearchEngine - __all__ = [ "WebSearchEngine", diff --git a/app/tool/search/bing_search.py b/app/tool/search/bing_search.py index c5eaa86..701841b 100644 --- a/app/tool/search/bing_search.py +++ b/app/tool/search/bing_search.py @@ -1,22 +1,24 @@ from typing import List + import requests -from app.logger import logger from bs4 import BeautifulSoup + +from app.logger import logger from app.tool.search.base import WebSearchEngine ABSTRACT_MAX_LENGTH = 300 USER_AGENTS = [ - 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36', - 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)', - 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/49.0.2623.108 Chrome/49.0.2623.108 Safari/537.36', - 'Mozilla/5.0 (Windows; U; Windows NT 5.1; pt-BR) AppleWebKit/533.3 (KHTML, like Gecko) QtWeb Internet Browser/3.7 http://www.QtWeb.net', - 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36', - 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) ChromePlus/4.0.222.3 Chrome/4.0.222.3 Safari/532.2', - 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.4pre) Gecko/20070404 K-Ninja/2.1.3', - 'Mozilla/5.0 (Future Star Technologies Corp.; Star-Blade OS; x86_64; U; en-US) iNet Browser 4.7', - 'Mozilla/5.0 (Windows; U; Windows NT 6.1; rv:2.2) Gecko/20110201', - 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.13) Gecko/20080414 Firefox/2.0.0.13 Pogo/2.0.0.13.6866' + "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36", + "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)", + "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Ubuntu Chromium/49.0.2623.108 Chrome/49.0.2623.108 Safari/537.36", + "Mozilla/5.0 (Windows; U; Windows NT 5.1; pt-BR) AppleWebKit/533.3 (KHTML, like Gecko) QtWeb Internet Browser/3.7 http://www.QtWeb.net", + "Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36", + "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/532.2 (KHTML, like Gecko) ChromePlus/4.0.222.3 Chrome/4.0.222.3 Safari/532.2", + "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.4pre) Gecko/20070404 K-Ninja/2.1.3", + "Mozilla/5.0 (Future Star Technologies Corp.; Star-Blade OS; x86_64; U; en-US) iNet Browser 4.7", + "Mozilla/5.0 (Windows; U; Windows NT 6.1; rv:2.2) Gecko/20110201", + "Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.13) Gecko/20080414 Firefox/2.0.0.13 Pogo/2.0.0.13.6866", ] HEADERS = { @@ -25,7 +27,7 @@ HEADERS = { "User-Agent": USER_AGENTS[0], "Referer": "https://www.bing.com/", "Accept-Encoding": "gzip, deflate", - "Accept-Language": "zh-CN,zh;q=0.9" + "Accept-Language": "zh-CN,zh;q=0.9", } BING_HOST_URL = "https://www.bing.com" @@ -65,7 +67,9 @@ class BingSearchEngine(WebSearchEngine): next_url = BING_SEARCH_URL + query while len(list_result) < num_results: - data, next_url = self._parse_html(next_url, rank_start=len(list_result), first=first) + data, next_url = self._parse_html( + next_url, rank_start=len(list_result), first=first + ) if data: list_result.extend([item["url"] for item in data]) if not next_url: @@ -98,14 +102,14 @@ class BingSearchEngine(WebSearchEngine): return [], None for li in ol_results.find_all("li", class_="b_algo"): - title = '' - url = '' - abstract = '' + title = "" + url = "" + abstract = "" try: h2 = li.find("h2") if h2: title = h2.text.strip() - url = h2.a['href'].strip() + url = h2.a["href"].strip() p = li.find("p") if p: @@ -115,7 +119,14 @@ class BingSearchEngine(WebSearchEngine): abstract = abstract[:ABSTRACT_MAX_LENGTH] rank_start += 1 - list_data.append({"title": title, "abstract": abstract, "url": url, "rank": rank_start}) + list_data.append( + { + "title": title, + "abstract": abstract, + "url": url, + "rank": rank_start, + } + ) except Exception: continue @@ -131,4 +142,4 @@ class BingSearchEngine(WebSearchEngine): def perform_search(self, query, num_results=10, *args, **kwargs): """Bing search engine.""" - return self._search_sync(query, num_results=num_results) \ No newline at end of file + return self._search_sync(query, num_results=num_results) diff --git a/app/tool/web_search.py b/app/tool/web_search.py index 99d8916..3647883 100644 --- a/app/tool/web_search.py +++ b/app/tool/web_search.py @@ -6,11 +6,11 @@ from tenacity import retry, stop_after_attempt, wait_exponential from app.config import config from app.tool.base import BaseTool from app.tool.search import ( - BaiduSearchEngine, + BaiduSearchEngine, + BingSearchEngine, DuckDuckGoSearchEngine, GoogleSearchEngine, - WebSearchEngine, - BingSearchEngine + WebSearchEngine ) @@ -38,7 +38,7 @@ class WebSearch(BaseTool): "google": GoogleSearchEngine(), "baidu": BaiduSearchEngine(), "duckduckgo": DuckDuckGoSearchEngine(), - "bing": BingSearchEngine() + "bing": BingSearchEngine(), } async def execute(self, query: str, num_results: int = 10) -> List[str]: From b9fdade6e42afacdc7622416d8d1856c43336e2d Mon Sep 17 00:00:00 2001 From: via Date: Wed, 19 Mar 2025 09:15:51 +0800 Subject: [PATCH 4/4] Apply black and isort formatting --- app/tool/web_search.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/app/tool/web_search.py b/app/tool/web_search.py index 3647883..8b80e46 100644 --- a/app/tool/web_search.py +++ b/app/tool/web_search.py @@ -6,7 +6,7 @@ from tenacity import retry, stop_after_attempt, wait_exponential from app.config import config from app.tool.base import BaseTool from app.tool.search import ( - BaiduSearchEngine, + BaiduSearchEngine, BingSearchEngine, DuckDuckGoSearchEngine, GoogleSearchEngine,