File size: 4,557 Bytes
3beb07e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 |
from contextlib import asynccontextmanager
from typing import Optional
from duckduckgo_search import DDGS
from pydantic import BaseModel
from playwright.async_api import Browser, BrowserContext, Page, TimeoutError
from urllib.parse import quote_plus
import logging
import re
class APIPatentResults(BaseModel):
"""Response of /search_patents endpoint"""
error: Optional[str]
results: Optional[list[dict]]
class APISearchResults(BaseModel):
error: Optional[str]
results: Optional[list[dict]]
class BraveSearchBlockedException(Exception):
"""Dummy exception to detect when the headless browser is flagged as suspicious."""
pass
@asynccontextmanager
async def playwright_open_page(browser: Browser):
"""Context manager for playwright pages"""
context: BrowserContext = await browser.new_context()
page: Page = await context.new_page()
try:
yield page
finally:
await page.close()
await context.close()
async def query_google_patents(browser: Browser, q: str, n_results: int = 10):
"""Queries google patents for the specified query and number of results. Returns relevant patents"""
async with playwright_open_page(browser) as page:
async def _block_resources(route, request):
if request.resource_type in ["stylesheet", "image"]:
await route.abort()
else:
await route.continue_()
await page.route("**/*", _block_resources)
url = f"https://patents.google.com/?q=({quote_plus(q)})&oq={quote_plus(q)}&num={n_results}"
await page.goto(url)
await page.wait_for_function(
f"""() => document.querySelectorAll('search-result-item').length >= {n_results}""",
timeout=30_000
)
# regex to locate a patent id
PATENT_ID_REGEX = r"\b[A-Z]{2}\d{6,}(?:[A-Z]\d?)?\b"
items = await page.locator("search-result-item").all()
id_matches = []
for item in items:
all_text = " ".join(await item.locator("span").all_inner_texts())
found = re.findall(PATENT_ID_REGEX, all_text)
if found:
id_matches.append(found[0])
patents = [{"href": f"https://patents.google.com/patent/{id}/en", "id": id}
for id in id_matches]
return patents[:n_results]
async def query_brave_search(browser: Browser, q: str, n_results: int = 10):
"""Queries Brave Search for the specified query."""
async with playwright_open_page(browser) as page:
async def _block_resources(route, request):
if request.resource_type in ["stylesheet", "image"]:
await route.abort()
else:
await route.continue_()
await page.route("**/*", _block_resources)
url = f"https://search.brave.com/search?q={quote_plus(q)}"
await page.goto(url)
results_cards = await page.locator('.snippet').all()
if len(results_cards) == 0:
logging.warning(f"No results for query: {q}")
page_content = await page.content()
if "suspicious" in page_content:
logging.warning("Brave search flagged browser as suspicious.")
raise BraveSearchBlockedException()
results = []
try:
for result in results_cards:
title = await result.locator('.title').all_inner_texts()
description = await result.locator('.snippet-description').all_inner_texts()
url = await result.locator('a').nth(0).get_attribute('href')
# Filter out results with no URL or brave-specific URLs
if url is None or url.startswith('/'):
continue
results.append({
"title": title[0] if title else "",
"body": description[0] if description else "",
"href": url
})
if len(results) >= n_results:
break
except TimeoutError as e:
logging.warning(
f"Timeout on selector while parsing Brave Search SERP: {e}")
return results
async def query_ddg_search(q: str, n_results: int = 10):
"""Queries duckduckgo search for the specified query"""
ddgs = DDGS()
results = []
for result in ddgs.text(q, max_results=n_results):
results.append(
{"title": result["title"], "body": result["body"], "href": result["href"]})
return results
|