Python کے ساتھ Bing سرچ نتائج کو کیسے اسکریپ کریں

pip install requests beautifulsoup4 lxml fake-useragent selenium

import time
import random
from typing import List, Dict
import requests
from bs4 import BeautifulSoup

BING_URL = "https://www.bing.com/search"

HEADERS_POOL = [
    # You can add more — or use fake-useragent
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
    "(KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 13_5) AppleWebKit/605.1.15 "
    "(KHTML, like Gecko) Version/17.0 Safari/605.1.15",
]

def fetch_serp(query: str, count: int = 10, first: int = 1,
               proxy: str | None = None) -> List[Dict]:
    """
Returns a list of results: title, url, snippet, position.
`first` — starting position (pagination), `count` — how many records to fetch.

    """
    params = {"q": query, "count": count, "first": first}
    headers = {"User-Agent": random.choice(HEADERS_POOL)}
    proxies = {"http": proxy, "https": proxy} if proxy else None

    resp = requests.get(BING_URL, params=params, headers=headers,
                        proxies=proxies, timeout=15)
    resp.raise_for_status()
    soup = BeautifulSoup(resp.text, "lxml")

   # Typical Bing markup: <li class="b_algo"> ... <h2><a href="">Title</a></h2>
    items = []
    for idx, li in enumerate(soup.select("li.b_algo"), start=first):
        a = li.select_one("h2 a")
        if not a:
            continue
        title = a.get_text(strip=True)
        url = a.get("href")
         # Snippet is often in .b_caption p or simply the first <p>
        sn_el = li.select_one(".b_caption p") or li.select_one("p")
        snippet = sn_el.get_text(" ", strip=True) if sn_el else ""
        items.append({
            "position": idx,
            "title": title,
            "url": url,
            "snippet": snippet
        })
    return items

if __name__ == "__main__":
    data = fetch_serp("python web scraping tutorial", count=10)
    for row in data:
        print(f"{row['position']:>2}. {row['title']} -- {row['url']}")
        print(f"   {row['snippet']}\n")

import requests

API_TOKEN = "apify_xxx"  # store in ENV
actor = "tri_angle/bing-search-scraper"
payload = {
    "queries": ["python web scraping tutorial"],
    "countryCode": "US",
    "includeUnfilteredResults": False
}

r = requests.post(
    f"https://api.apify.com/v2/acts/{actor}/runs?token={API_TOKEN}",
    json=payload, timeout=30
)
run = r.json()
# Retrieve dataset items using run['data']['defaultDatasetId']

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.options import Options

def selenium_bing(query: str, headless: bool = True):
    opts = Options()
    if headless:
        opts.add_argument("--headless=new")
    opts.add_argument("--disable-gpu")
    opts.add_argument("--no-sandbox")
    with webdriver.Chrome(options=opts) as driver:
        driver.get("https://www.bing.com/")
        box = driver.find_element(By.NAME, "q")
        box.send_keys(query)
        box.submit()

        # Consider adding explicit waits via WebDriverWait
        cards = driver.find_elements(By.CSS_SELECTOR, "li.b_algo h2 a")
        results = []
        for i, a in enumerate(cards, start=1):
            results.append({"position": i, "title": a.text, "url": a.get_attribute("href")})
        return results

if __name__ == "__main__":
    print(selenium_bing("site:docs.python.org requests headers"))

from __future__ import annotations

import argparse
import csv
import dataclasses
import pathlib
import random
import sys
import time
from typing import List, Optional, Tuple

import requests
from bs4 import BeautifulSoup, FeatureNotFound

BING_URL = "https://www.bing.com/search"

# Pool of user agents
UA_POOL = [
    "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36",
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 13_6) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.5 Safari/605.1.15",
    "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36",
]

@dataclasses.dataclass
class SerpItem:
    position: int
    title: str
    url: str
    snippet: str


def build_session(proxy: Optional[str] = None) -> requests.Session:
    """Create a session with baseline headers and an optional proxy."""
    s = requests.Session()
    s.headers.update(
        {
            "User-Agent": random.choice(UA_POOL),
            "Accept-Language": "uk-UA,uk;q=0.9,en;q=0.8",
            "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
        }
    )
    if proxy:
        # Requests proxy dict format: {'http': 'http://host:port', 'https': 'http://host:port'}
        s.proxies.update({"http": proxy, "https": proxy})
    return s


def _soup_with_fallback(html: str) -> BeautifulSoup:
    """Parse HTML with a forgiving fallback chain: lxml -> html.parser -> html5lib (if available)."""
    for parser in ("lxml", "html.parser", "html5lib"):
        try:
            return BeautifulSoup(html, parser)
        except FeatureNotFound:
            continue
    # If none are installed, bs4 will raise; let it propagate
    return BeautifulSoup(html, "html.parser")


def parse_serp_html(html: str, start_pos: int) -> List[SerpItem]:
    """Extract organic results from Bing SERP HTML."""
    soup = _soup_with_fallback(html)
    items: List[SerpItem] = []

    # Organic blocks typically look like <li class="b_algo"> with h2>a and a snippet under .b_caption p or the first <p>.
    for i, li in enumerate(soup.select("li.b_algo"), start=start_pos):
        a = li.select_one("h2 > a")
        if not a:
            continue
        title = (a.get_text(strip=True) or "").strip()
        url = a.get("href") or ""
        p = li.select_one(".b_caption p") or li.select_one("p")
        snippet = (p.get_text(" ", strip=True) if p else "").strip()
        items.append(SerpItem(position=i, title=title, url=url, snippet=snippet))

    return items


def fetch_bing_page(
    session: requests.Session,
    query: str,
    first: int = 1,
    count: int = 10,
    cc: str = "UA",
    setlang: str = "uk",
    timeout: int = 20,
) -> List[SerpItem]:
    """Download one results page and return parsed items."""
    params = {
        "q": query,
        "count": count,   # 10, 15, 20...
        "first": first,   # 1, 11, 21...
        "cc": cc,         # country code for results
        "setlang": setlang,  # interface/snippet language
    }
    r = session.get(BING_URL, params=params, timeout=timeout)
    r.raise_for_status()
    return parse_serp_html(r.text, start_pos=first)


def search_bing(
    query: str,
    pages: int = 1,
    count: int = 10,
    pause_range: Tuple[float, float] = (1.2, 2.7),
    proxy: Optional[str] = None,
    cc: str = "UA",
    setlang: str = "uk",
    timeout: int = 20,
) -> List[SerpItem]:
    """Iterate over pages and return an aggregated list of results."""
    session = build_session(proxy=proxy)
    all_items: List[SerpItem] = []
    first = 1
    for _ in range(pages):
        items = fetch_bing_page(
            session, query, first=first, count=count, cc=cc, setlang=setlang, timeout=timeout
        )
        all_items.extend(items)
        time.sleep(random.uniform(*pause_range))  # polite delay
        first += count
    return all_items


def _normalize_cell(s: str) -> str:
    """Optional: collapse internal whitespace so simple viewers show one‑line cells."""
    # Convert tabs/newlines/multiple spaces to a single space
    return " ".join((s or "").split())


def save_csv(
    items: List[SerpItem],
    path: str,
    excel_friendly: bool = False,
    normalize: bool = False,
    delimiter: str = ",",
) -> int:
    """
Write results to CSV.
— excel_friendly=True -> write UTF‑8 with BOM (utf‑8‑sig) so Excel auto‑detects Unicode.
— normalize=True -> collapse whitespace inside string fields.
— delimiter -> change if your consumer expects ';', etc.
Returns the number of rows written (excluding header).

    """
    p = pathlib.Path(path)
    p.parent.mkdir(parents=True, exist_ok=True)

    encoding = "utf-8-sig" if excel_friendly else "utf-8"

    # newline='' is required so Python's csv handles line endings correctly on all platforms
    with p.open("w", newline="", encoding=encoding) as f:
        writer = csv.DictWriter(
            f,
            fieldnames=["position", "title", "url", "snippet"],
            delimiter=delimiter,
            quoting=csv.QUOTE_MINIMAL,
        )
        writer.writeheader()
        for it in items:
            row = dataclasses.asdict(it)
            if normalize:
                row = {k: _normalize_cell(v) if isinstance(v, str) else v for k, v in row.items()}
            writer.writerow(row)
    return len(items)


def main() -> int:
    ap = argparse.ArgumentParser(description="Bing SERP scraper (Requests + BS4)")
    ap.add_argument("-q", "--query", required=True, help="Search query")
    ap.add_argument("--pages", type=int, default=1, help="Number of pages (x count)")
    ap.add_argument("--count", type=int, default=10, help="Results per page")
    ap.add_argument("--cc", default="UA", help="Country code for results (cc)")
    ap.add_argument("--setlang", default="uk", help="Interface/snippet language (setlang)")
    ap.add_argument("--proxy", help="Proxy, e.g. http://user:pass@host:port")
    ap.add_argument("--csv", help="Path to CSV to save results")
    ap.add_argument(
        "--excel-friendly",
        action="store_true",
        help="Add BOM (UTF‑8‑SIG) so Excel opens the file correctly",
    )
    ap.add_argument(
        "--normalize-cells",
        action="store_true",
        help="Remove line breaks and extra spaces in cells",
    )
    ap.add_argument(
        "--delimiter",
        default=",",
        help="CSV delimiter (default ','); e.g.: ';'",
    )
    args = ap.parse_args()

    try:
        items = search_bing(
            args.query,
            pages=args.pages,
            count=args.count,
            proxy=args.proxy,
            cc=args.cc,
            setlang=args.setlang,
        )
    except requests.HTTPError as e:
        print(f"[ERROR] HTTP error: {e}", file=sys.stderr)
        return 2
    except requests.RequestException as e:
        print(f"[ERROR] Network error: {e}", file=sys.stderr)
        return 2

    if args.csv:
        try:
            n = save_csv(
                items,
                args.csv,
                excel_friendly=args.excel_friendly,
                normalize=args.normalize_cells,
                delimiter=args.delimiter,
            )
            print(f"Saved {n} rows to {args.csv}")
        except OSError as e:
            print(f"[ERROR] Could not write CSV to {args.csv}: {e}", file=sys.stderr)
            return 3
    else:
        for it in items:
            print(f"{it.position:>2}. {it.title} -- {it.url}")
            if it.snippet:
                print("   ", it.snippet[:180])

    return 0


if __name__ == "__main__":
    sys.exit(main())

python bing_scraper.py -q "Python web scraping" --pages 3 --csv out.csv \
  --proxy "http://username:password@proxy:port"