2023-12-02 08:14:36 +00:00
|
|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
# @Author : relakkes@gmail.com
|
|
|
|
|
# @Time : 2023/12/2 12:53
|
|
|
|
|
# @Desc : 爬虫相关的工具函数
|
|
|
|
|
|
|
|
|
|
import base64
|
|
|
|
|
import random
|
|
|
|
|
import re
|
|
|
|
|
from io import BytesIO
|
|
|
|
|
from typing import Dict, List, Optional, Tuple
|
|
|
|
|
|
2023-12-30 10:54:21 +00:00
|
|
|
import httpx
|
2023-12-02 08:14:36 +00:00
|
|
|
from PIL import Image, ImageDraw
|
|
|
|
|
from playwright.async_api import Cookie, Page
|
|
|
|
|
|
2024-08-05 19:37:55 +00:00
|
|
|
from proxy import IpInfoModel
|
2024-08-08 06:19:32 +00:00
|
|
|
|
2023-12-30 10:54:21 +00:00
|
|
|
from . import utils
|
|
|
|
|
|
2023-12-02 08:14:36 +00:00
|
|
|
|
|
|
|
|
async def find_login_qrcode(page: Page, selector: str) -> str:
|
|
|
|
|
"""find login qrcode image from target selector"""
|
|
|
|
|
try:
|
|
|
|
|
elements = await page.wait_for_selector(
|
|
|
|
|
selector=selector,
|
|
|
|
|
)
|
2023-12-30 10:54:21 +00:00
|
|
|
login_qrcode_img = str(await elements.get_property("src")) # type: ignore
|
|
|
|
|
if "http://" in login_qrcode_img or "https://" in login_qrcode_img:
|
|
|
|
|
async with httpx.AsyncClient(follow_redirects=True) as client:
|
|
|
|
|
utils.logger.info(f"[find_login_qrcode] get qrcode by url:{login_qrcode_img}")
|
|
|
|
|
resp = await client.get(login_qrcode_img, headers={"User-Agent": get_user_agent()})
|
|
|
|
|
if resp.status_code == 200:
|
|
|
|
|
image_data = resp.content
|
|
|
|
|
base64_image = base64.b64encode(image_data).decode('utf-8')
|
|
|
|
|
return base64_image
|
|
|
|
|
raise Exception(f"fetch login image url failed, response message:{resp.text}")
|
|
|
|
|
return login_qrcode_img
|
2023-12-02 08:14:36 +00:00
|
|
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
print(e)
|
|
|
|
|
return ""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def show_qrcode(qr_code) -> None: # type: ignore
|
|
|
|
|
"""parse base64 encode qrcode image and show it"""
|
2023-12-30 10:54:21 +00:00
|
|
|
if "," in qr_code:
|
|
|
|
|
qr_code = qr_code.split(",")[1]
|
2023-12-02 08:14:36 +00:00
|
|
|
qr_code = base64.b64decode(qr_code)
|
|
|
|
|
image = Image.open(BytesIO(qr_code))
|
|
|
|
|
|
|
|
|
|
# Add a square border around the QR code and display it within the border to improve scanning accuracy.
|
|
|
|
|
width, height = image.size
|
|
|
|
|
new_image = Image.new('RGB', (width + 20, height + 20), color=(255, 255, 255))
|
|
|
|
|
new_image.paste(image, (10, 10))
|
|
|
|
|
draw = ImageDraw.Draw(new_image)
|
|
|
|
|
draw.rectangle((0, 0, width + 19, height + 19), outline=(0, 0, 0), width=1)
|
|
|
|
|
new_image.show()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_user_agent() -> str:
|
|
|
|
|
ua_list = [
|
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.79 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.53 Safari/537.36",
|
2024-03-16 17:03:56 +00:00
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.84 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/123.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.5112.79 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/121.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.5060.53 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.4844.84 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.5112.79 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/112.0.5060.53 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.4844.84 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.5112.79 Safari/537.36"
|
2023-12-02 08:14:36 +00:00
|
|
|
]
|
|
|
|
|
return random.choice(ua_list)
|
|
|
|
|
|
|
|
|
|
|
2023-12-24 16:02:11 +00:00
|
|
|
def get_mobile_user_agent() -> str:
|
|
|
|
|
ua_list = [
|
|
|
|
|
"Mozilla/5.0 (iPhone; CPU iPhone OS 16_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.5 Mobile/15E148 Safari/604.1",
|
|
|
|
|
"Mozilla/5.0 (iPad; CPU OS 16_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.5 Mobile/15E148 Safari/604.1",
|
|
|
|
|
"Mozilla/5.0 (iPhone; CPU iPhone OS 16_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) CriOS/114.0.5735.99 Mobile/15E148 Safari/604.1",
|
|
|
|
|
"Mozilla/5.0 (iPad; CPU OS 16_5 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) CriOS/114.0.5735.124 Mobile/15E148 Safari/604.1",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 10; K) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Mobile Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 13; SAMSUNG SM-S918B) AppleWebKit/537.36 (KHTML, like Gecko) SamsungBrowser/21.0 Chrome/110.0.5481.154 Mobile Safari/537.36",
|
|
|
|
|
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36 OPR/99.0.0.0",
|
|
|
|
|
"Mozilla/5.0 (Linux; Android 10; JNY-LX1; HMSCore 6.11.0.302) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.88 HuaweiBrowser/13.0.5.303 Mobile Safari/537.36"
|
|
|
|
|
]
|
|
|
|
|
return random.choice(ua_list)
|
|
|
|
|
|
|
|
|
|
|
2023-12-02 08:14:36 +00:00
|
|
|
def convert_cookies(cookies: Optional[List[Cookie]]) -> Tuple[str, Dict]:
|
|
|
|
|
if not cookies:
|
|
|
|
|
return "", {}
|
|
|
|
|
cookies_str = ";".join([f"{cookie.get('name')}={cookie.get('value')}" for cookie in cookies])
|
|
|
|
|
cookie_dict = dict()
|
|
|
|
|
for cookie in cookies:
|
|
|
|
|
cookie_dict[cookie.get('name')] = cookie.get('value')
|
|
|
|
|
return cookies_str, cookie_dict
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def convert_str_cookie_to_dict(cookie_str: str) -> Dict:
|
|
|
|
|
cookie_dict: Dict[str, str] = dict()
|
|
|
|
|
if not cookie_str:
|
|
|
|
|
return cookie_dict
|
|
|
|
|
for cookie in cookie_str.split(";"):
|
|
|
|
|
cookie = cookie.strip()
|
|
|
|
|
if not cookie:
|
|
|
|
|
continue
|
|
|
|
|
cookie_list = cookie.split("=")
|
|
|
|
|
if len(cookie_list) != 2:
|
|
|
|
|
continue
|
|
|
|
|
cookie_value = cookie_list[1]
|
|
|
|
|
if isinstance(cookie_value, list):
|
|
|
|
|
cookie_value = "".join(cookie_value)
|
|
|
|
|
cookie_dict[cookie_list[0]] = cookie_value
|
|
|
|
|
return cookie_dict
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def match_interact_info_count(count_str: str) -> int:
|
|
|
|
|
if not count_str:
|
|
|
|
|
return 0
|
|
|
|
|
|
|
|
|
|
match = re.search(r'\d+', count_str)
|
|
|
|
|
if match:
|
|
|
|
|
number = match.group()
|
|
|
|
|
return int(number)
|
|
|
|
|
else:
|
|
|
|
|
return 0
|
2024-08-05 19:37:55 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
def format_proxy_info(ip_proxy_info: IpInfoModel) -> Tuple[Optional[Dict], Optional[Dict]]:
|
|
|
|
|
"""format proxy info for playwright and httpx"""
|
|
|
|
|
playwright_proxy = {
|
|
|
|
|
"server": f"{ip_proxy_info.protocol}{ip_proxy_info.ip}:{ip_proxy_info.port}",
|
|
|
|
|
"username": ip_proxy_info.user,
|
|
|
|
|
"password": ip_proxy_info.password,
|
|
|
|
|
}
|
|
|
|
|
httpx_proxy = {
|
|
|
|
|
f"{ip_proxy_info.protocol}": f"http://{ip_proxy_info.user}:{ip_proxy_info.password}@{ip_proxy_info.ip}:{ip_proxy_info.port}"
|
|
|
|
|
}
|
2024-08-06 18:39:50 +00:00
|
|
|
return playwright_proxy, httpx_proxy
|
|
|
|
|
|
|
|
|
|
def extract_text_from_html(html: str) -> str:
|
|
|
|
|
"""Extract text from HTML, removing all tags."""
|
|
|
|
|
# Remove script and style elements
|
|
|
|
|
clean_html = re.sub(r'<(script|style)[^>]*>.*?</\1>', '', html, flags=re.DOTALL)
|
|
|
|
|
# Remove all other tags
|
|
|
|
|
clean_text = re.sub(r'<[^>]+>', '', clean_html).strip()
|
|
|
|
|
return clean_text
|
