Commit
·
36092a0
1
Parent(s):
be7cc52
Using google search
Browse files
test1.py
CHANGED
|
@@ -1,38 +1,44 @@
|
|
| 1 |
from fastapi import FastAPI
|
| 2 |
-
from playwright.async_api import async_playwright
|
|
|
|
| 3 |
|
| 4 |
app = FastAPI()
|
| 5 |
|
| 6 |
async def scrape_google(query: str):
|
| 7 |
-
url =
|
| 8 |
-
"https://www.google.com/search"
|
| 9 |
-
f"?q={query}"
|
| 10 |
-
"&sxsrf=AE3TifOZcTbH54cOkE27wqRqSVEmaqb7fw%3A1750003707838"
|
| 11 |
-
)
|
| 12 |
async with async_playwright() as pw:
|
| 13 |
browser = await pw.chromium.launch(headless=True)
|
| 14 |
context = await browser.new_context()
|
| 15 |
page = await context.new_page()
|
| 16 |
|
| 17 |
-
|
| 18 |
try:
|
| 19 |
-
|
| 20 |
-
|
| 21 |
-
except:
|
| 22 |
pass
|
| 23 |
|
| 24 |
-
|
| 25 |
-
await page.wait_for_selector("h3")
|
| 26 |
-
|
| 27 |
-
results = []
|
| 28 |
for h in await page.query_selector_all("h3"):
|
| 29 |
try:
|
| 30 |
-
|
|
|
|
| 31 |
title = await h.inner_text()
|
| 32 |
-
|
| 33 |
except:
|
| 34 |
continue
|
| 35 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
await browser.close()
|
| 37 |
return results
|
| 38 |
|
|
|
|
| 1 |
from fastapi import FastAPI
|
| 2 |
+
from playwright.async_api import async_playwright, TimeoutError
|
| 3 |
+
import re
|
| 4 |
|
| 5 |
app = FastAPI()
|
| 6 |
|
| 7 |
async def scrape_google(query: str):
|
| 8 |
+
url = f"https://www.google.com/search?q={query}"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
async with async_playwright() as pw:
|
| 10 |
browser = await pw.chromium.launch(headless=True)
|
| 11 |
context = await browser.new_context()
|
| 12 |
page = await context.new_page()
|
| 13 |
|
| 14 |
+
await page.goto(url, wait_until="domcontentloaded", timeout=60000)
|
| 15 |
try:
|
| 16 |
+
await page.wait_for_selector("div#search", timeout=10000)
|
| 17 |
+
except TimeoutError:
|
|
|
|
| 18 |
pass
|
| 19 |
|
| 20 |
+
links = []
|
|
|
|
|
|
|
|
|
|
| 21 |
for h in await page.query_selector_all("h3"):
|
| 22 |
try:
|
| 23 |
+
a = await h.evaluate_handle("e => e.closest('a')")
|
| 24 |
+
href = await a.get_attribute("href")
|
| 25 |
title = await h.inner_text()
|
| 26 |
+
links.append({"title": title, "link": href})
|
| 27 |
except:
|
| 28 |
continue
|
| 29 |
|
| 30 |
+
results = []
|
| 31 |
+
for item in links[:5]:
|
| 32 |
+
await page.goto(item["link"], wait_until="domcontentloaded", timeout=30000)
|
| 33 |
+
html = await page.content()
|
| 34 |
+
emails = re.findall(r"[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}", html)
|
| 35 |
+
phones = re.findall(r"\+?\d[\d\s\-/]{7,}\d", html)
|
| 36 |
+
results.append({
|
| 37 |
+
**item,
|
| 38 |
+
"emails": list(set(emails))[:2],
|
| 39 |
+
"phones": list(set(phones))[:2]
|
| 40 |
+
})
|
| 41 |
+
|
| 42 |
await browser.close()
|
| 43 |
return results
|
| 44 |
|