File size: 7,933 Bytes
3beb07e a007a27 3beb07e c38bd79 3beb07e e14c7a4 3beb07e e14c7a4 3beb07e e14c7a4 3beb07e e14c7a4 3beb07e e14c7a4 3beb07e 8d6fbc5 3beb07e e14c7a4 8d6fbc5 3beb07e e14c7a4 8d6fbc5 e14c7a4 8d6fbc5 3beb07e cd59c29 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 |
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 SerpResults(BaseModel):
"""Model for SERP scrapping results"""
error: Optional[str]
results: Optional[list[dict]]
class BraveSearchBlockedException(Exception):
"""Dummy exception to detect when the headless browser is flagged as suspicious."""
def __init__(self, *args):
super().__init__("Brave Search blocked the request, likely due to flagging browser 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_scholar(browser: Browser, q: str, n_results: int = 10):
"""Queries google scholar for the specified query and number of results. Returns relevant papers"""
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://scholar.google.com/scholar?q={quote_plus(q)}&num={n_results}"
await page.goto(url)
await page.wait_for_selector("div.gs_ri")
items = await page.locator("div.gs_ri").all()
results = []
for item in items[:n_results]:
title = await item.locator("h3").inner_text(timeout=1000)
body = await item.locator("div.gs_rs").inner_text(timeout=1000)
href = await item.locator("h3 > a").get_attribute("href")
results.append({
"title": title,
"body": body,
"href": href
})
return results
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"""
# regex to locate a patent id
PATENT_ID_REGEX = r"\b[A-Z]{2}\d{6,}(?:[A-Z]\d?)?\b"
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)}&num={n_results}"
await page.goto(url)
# Wait for at least one search result item to appear
# This ensures the page has loaded enough to start scraping
await page.wait_for_function(
f"""() => document.querySelectorAll('search-result-item').length >= 1""",
timeout=30_000
)
items = await page.locator("search-result-item").all()
results = []
for item in items:
text = " ".join(await item.locator("span").all_inner_texts())
match = re.search(PATENT_ID_REGEX, text)
if not match:
continue
patent_id = match.group()
try:
title = await item.locator("h3, h4").first.inner_text(timeout=1000)
body = await item.locator("div.abstract, div.result-snippet, .snippet, .result-text").first.inner_text(timeout=1000)
except:
continue # If we can't get title or body, skip this item
results.append({
"id": patent_id,
"href": f"https://patents.google.com/patent/{patent_id}/en",
"title": title,
"body": body
})
return results[: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:
page_content = await page.content()
if "suspicious" in page_content:
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_bing_search(browser: Browser, q: str, n_results: int = 10):
"""Queries bing 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://www.bing.com/search?q={quote_plus(q)}"
await page.goto(url)
await page.wait_for_selector("li.b_algo")
results = []
items = await page.query_selector_all("li.b_algo")
for item in items[:n_results]:
title_el = await item.query_selector("h2 > a")
url = await title_el.get_attribute("href") if title_el else None
title = await title_el.inner_text() if title_el else ""
snippet = ""
# Try several fallback selectors
for selector in [
"div.b_caption p", # typical snippet
"div.b_caption", # sometimes snippet is here
"div.b_snippet", # used in some result types
"div.b_text", # used in some panels
"p" # fallback to any paragraph
]:
snippet_el = await item.query_selector(selector)
if snippet_el:
snippet = await snippet_el.inner_text()
if snippet.strip():
break
if title and url:
results.append({
"title": title.strip(),
"href": url.strip(),
"body": snippet.strip()
})
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
|