From ff9c1576b66654fdc9bd325d4a002dbb69b23f0e Mon Sep 17 00:00:00 2001 From: martin legrand Date: Fri, 4 Apr 2025 11:56:11 +0200 Subject: [PATCH] feat : better numerical value handling on webpage --- sources/agents/browser_agent.py | 7 ++++--- sources/browser.py | 20 ++++++++++++-------- 2 files changed, 16 insertions(+), 11 deletions(-) diff --git a/sources/agents/browser_agent.py b/sources/agents/browser_agent.py index 1608620..812b812 100644 --- a/sources/agents/browser_agent.py +++ b/sources/agents/browser_agent.py @@ -90,7 +90,7 @@ class BrowserAgent(Agent): {remaining_links_text} Your task: - 1. Decide if the current page answers the user’s query: {user_prompt} + 1. Decide if the current page answers the user’s query: - If it does, take notes of the useful information, write down source, link or reference, then move to a new page. - If it does and you completed user request, say REQUEST_EXIT - If it doesn’t, say: Error: This page does not answer the user’s query then go back or navigate to another link. @@ -120,7 +120,7 @@ class BrowserAgent(Agent): GO_BACK Example 3 (query answer found): - Note: I found on github.com that agenticSeek is Fosowl. + Note: I found on github.com that agenticSeek is made by Fosowl. Given this information, given this I should exit the web browser. REQUEST_EXIT Example 4 (loging form visible): @@ -131,7 +131,8 @@ class BrowserAgent(Agent): You see the following inputs forms: {inputs_form_text} - Remember, the user asked: {user_prompt} + Remember, the user asked: + {user_prompt} So far you took these notes: {notes} You are currently on page : {self.current_page} diff --git a/sources/browser.py b/sources/browser.py index 82259e8..37930ba 100644 --- a/sources/browser.py +++ b/sources/browser.py @@ -22,7 +22,10 @@ import logging import sys import re -from sources.utility import pretty_print, animate_thinking +if __name__ == "__main__": + from utility import pretty_print, animate_thinking +else: + from sources.utility import pretty_print, animate_thinking logging.basicConfig(filename='browser.log', level=logging.ERROR, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s') @@ -155,13 +158,12 @@ class Browser: """Check if the text qualifies as a meaningful sentence or contains important error codes.""" text = text.strip() - error_codes = ["404", "403", "500", "502", "503"] - if any(code in text for code in error_codes): + if any(c.isdigit() for c in text): return True words = re.findall(r'\w+', text, re.UNICODE) word_count = len(words) has_punctuation = any(text.endswith(p) for p in ['.', '，', ',', '!', '?', '。', '！', '？', '।', '۔']) - is_long_enough = word_count > 5 + is_long_enough = word_count > 4 return (word_count >= 5 and (has_punctuation or is_long_enough)) def get_text(self) -> str | None: @@ -173,9 +175,8 @@ class Browser: element.decompose() text = soup.get_text() - lines = (line.strip() for line in text.splitlines()) - chunks = (phrase.strip() for line in lines for phrase in line.split(" ")) - text = "\n".join(chunk for chunk in chunks if chunk and self.is_sentence(chunk)) + lines = (f"{line.strip()}\n" for line in text.splitlines()) + text = "\n".join(chunk for chunk in lines if chunk and self.is_sentence(chunk)) text = text[:4096] #markdown_text = markdownify.markdownify(text, heading_style="ATX") return "[Start of page]\n" + text + "\n[End of page]" @@ -448,6 +449,9 @@ if __name__ == "__main__": browser = Browser(driver, anticaptcha_manual_install=True) time.sleep(10) + #browser.go_to("https://coinmarketcap.com/") + #txt = browser.get_text() + #print(txt) print("AntiCaptcha / Form Test") browser.go_to("https://www.google.com/recaptcha/api2/demo") #browser.go_to("https://practicetestautomation.com/practice-test-login/") @@ -456,4 +460,4 @@ if __name__ == "__main__": inputs = ['[input1](Martin)', f'[input2](Test)', '[input3](test@gmail.com)'] browser.fill_form_inputs(inputs) browser.find_and_click_submission() - time.sleep(30) + time.sleep(10)