xhs_crawler/media_platform/douyin/core.py

182 lines
7.7 KiB
Python
Raw Normal View History

import asyncio
2023-07-29 07:35:40 +00:00
import os
2023-06-25 13:05:30 +00:00
from asyncio import Task
2023-07-29 07:35:40 +00:00
from typing import Dict, List, Optional, Tuple
2023-07-29 07:35:40 +00:00
from playwright.async_api import (BrowserContext, BrowserType, Page,
async_playwright)
import config
2023-07-29 07:35:40 +00:00
from base.base_crawler import AbstractCrawler
from base.proxy_account_pool import AccountPool
from models import douyin
from tools import utils
2023-08-16 11:49:41 +00:00
from var import request_keyword_var
2023-07-29 07:35:40 +00:00
from .client import DOUYINClient
2023-06-25 13:05:30 +00:00
from .exception import DataFetchError
from .login import DouYinLogin
class DouYinCrawler(AbstractCrawler):
2023-07-29 07:35:40 +00:00
platform: str
login_type: str
context_page: Page
dy_client: DOUYINClient
2023-07-29 07:35:40 +00:00
account_pool: AccountPool
browser_context: BrowserContext
def __init__(self) -> None:
2023-06-25 13:05:30 +00:00
self.user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36" # fixed
self.index_url = "https://www.douyin.com"
2023-07-29 07:35:40 +00:00
def init_config(self, platform: str, login_type: str, account_pool: AccountPool) -> None:
self.platform = platform
self.login_type = login_type
self.account_pool = account_pool
async def start(self) -> None:
account_phone, playwright_proxy, httpx_proxy = self.create_proxy_info()
async with async_playwright() as playwright:
# Launch a browser context.
chromium = playwright.chromium
self.browser_context = await self.launch_browser(
chromium,
playwright_proxy,
self.user_agent,
headless=config.HEADLESS
)
# stealth.min.js is a js script to prevent the website from detecting the crawler.
await self.browser_context.add_init_script(path="libs/stealth.min.js")
self.context_page = await self.browser_context.new_page()
await self.context_page.goto(self.index_url)
self.dy_client = await self.create_douyin_client(httpx_proxy)
if not await self.dy_client.ping(browser_context=self.browser_context):
login_obj = DouYinLogin(
2023-07-29 07:35:40 +00:00
login_type=self.login_type,
login_phone=account_phone,
browser_context=self.browser_context,
context_page=self.context_page,
cookie_str=config.COOKIES
)
await login_obj.begin()
await self.dy_client.update_cookies(browser_context=self.browser_context)
2023-06-25 13:05:30 +00:00
# search_posts
2023-07-29 07:35:40 +00:00
await self.search()
2023-06-25 13:05:30 +00:00
utils.logger.info("Douyin Crawler finished ...")
2023-07-29 07:35:40 +00:00
async def search(self) -> None:
utils.logger.info("Begin search douyin keywords")
for keyword in config.KEYWORDS.split(","):
2023-08-16 11:49:41 +00:00
request_keyword_var.set(keyword)
utils.logger.info(f"Current keyword: {keyword}")
2023-06-25 13:05:30 +00:00
aweme_list: List[str] = []
2023-08-16 11:49:41 +00:00
dy_limit_count = 10 # douyin fixed limit page 10
2023-06-25 13:05:30 +00:00
page = 0
2023-08-16 11:49:41 +00:00
while (page + 1) * dy_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
2023-06-25 13:05:30 +00:00
try:
2023-07-29 07:35:40 +00:00
posts_res = await self.dy_client.search_info_by_keyword(keyword=keyword,
2023-08-16 11:49:41 +00:00
offset=page * dy_limit_count)
2023-06-25 13:05:30 +00:00
except DataFetchError:
2023-07-15 14:25:56 +00:00
utils.logger.error(f"search douyin keyword: {keyword} failed")
2023-06-25 13:05:30 +00:00
break
page += 1
for post_item in posts_res.get("data"):
try:
aweme_info: Dict = post_item.get("aweme_info") or \
post_item.get("aweme_mix_info", {}).get("mix_items")[0]
except TypeError:
continue
aweme_list.append(aweme_info.get("aweme_id", ""))
2023-06-25 13:05:30 +00:00
await douyin.update_douyin_aweme(aweme_item=aweme_info)
utils.logger.info(f"keyword:{keyword}, aweme_list:{aweme_list}")
2023-08-16 11:49:41 +00:00
await self.batch_get_note_comments(aweme_list)
2023-06-25 13:05:30 +00:00
2023-08-16 11:49:41 +00:00
async def batch_get_note_comments(self, aweme_list: List[str]) -> None:
2023-06-25 13:05:30 +00:00
task_list: List[Task] = []
2023-07-29 07:35:40 +00:00
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
2023-06-25 13:05:30 +00:00
for aweme_id in aweme_list:
2023-08-16 11:49:41 +00:00
task = asyncio.create_task(self.get_comments(aweme_id, semaphore), name=aweme_id)
2023-06-25 13:05:30 +00:00
task_list.append(task)
await asyncio.wait(task_list)
2023-08-16 11:49:41 +00:00
async def get_comments(self, aweme_id: str, semaphore: asyncio.Semaphore) -> None:
async with semaphore:
try:
await self.dy_client.get_aweme_all_comments(
aweme_id=aweme_id,
2023-08-16 05:58:44 +00:00
callback=douyin.batch_update_dy_aweme_comments,
)
utils.logger.info(f"aweme_id: {aweme_id} comments have all been obtained completed ...")
except DataFetchError as e:
utils.logger.error(f"aweme_id: {aweme_id} get comments failed, error: {e}")
def create_proxy_info(self) -> Tuple[Optional[str], Optional[Dict], Optional[str]]:
"""Create proxy info for playwright and httpx"""
if not config.ENABLE_IP_PROXY:
return None, None, None
# phone: 13012345671 ip_proxy: 111.122.xx.xx1:8888
phone, ip_proxy = self.account_pool.get_account() # type: ignore
playwright_proxy = {
"server": f"{config.IP_PROXY_PROTOCOL}{ip_proxy}",
"username": config.IP_PROXY_USER,
"password": config.IP_PROXY_PASSWORD,
}
httpx_proxy = f"{config.IP_PROXY_PROTOCOL}{config.IP_PROXY_USER}:{config.IP_PROXY_PASSWORD}@{ip_proxy}"
return phone, playwright_proxy, httpx_proxy
async def create_douyin_client(self, httpx_proxy: Optional[str]) -> DOUYINClient:
"""Create douyin client"""
cookie_str, cookie_dict = utils.convert_cookies(await self.browser_context.cookies()) # type: ignore
douyin_client = DOUYINClient(
proxies=httpx_proxy,
headers={
"User-Agent": self.user_agent,
"Cookie": cookie_str,
"Host": "www.douyin.com",
"Origin": "https://www.douyin.com/",
"Referer": "https://www.douyin.com/",
"Content-Type": "application/json;charset=UTF-8"
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
)
return douyin_client
async def launch_browser(
self,
chromium: BrowserType,
playwright_proxy: Optional[Dict],
user_agent: Optional[str],
headless: bool = True
) -> BrowserContext:
"""Launch browser and create browser context"""
if config.SAVE_LOGIN_STATE:
user_data_dir = os.path.join(os.getcwd(), "browser_data",
2023-07-29 07:35:40 +00:00
config.USER_DATA_DIR % self.platform) # type: ignore
browser_context = await chromium.launch_persistent_context(
user_data_dir=user_data_dir,
accept_downloads=True,
headless=headless,
proxy=playwright_proxy, # type: ignore
viewport={"width": 1920, "height": 1080},
user_agent=user_agent
) # type: ignore
return browser_context
else:
browser = await chromium.launch(headless=headless, proxy=playwright_proxy) # type: ignore
browser_context = await browser.new_context(
viewport={"width": 1920, "height": 1080},
user_agent=user_agent
)
return browser_context
2023-07-29 07:35:40 +00:00
async def close(self) -> None:
"""Close browser context"""
await self.browser_context.close()
utils.logger.info("Browser context closed ...")