jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-07 18:37:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

refactor: 优化代码

Browse Source
This commit is contained in:
Relakkes
2023-07-29 15:35:40 +08:00
parent febbb133d7
commit 4ff2cf8661
17 changed files with 133 additions and 140 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
media_platform/douyin/core.py
View File

@@ -1,38 +1,38 @@
import os
import asyncio
import os
from asyncio import Task
from argparse import Namespace
from typing import Optional, List, Dict, Tuple
from typing import Dict, List, Optional, Tuple
from playwright.async_api import async_playwright
from playwright.async_api import BrowserType
from playwright.async_api import BrowserContext
from playwright.async_api import Page
from playwright.async_api import (BrowserContext, BrowserType, Page,
async_playwright)
import config
from tools import utils
from .client import DOUYINClient
from .exception import DataFetchError
from .login import DouYinLogin
from base.base_crawler import AbstractCrawler
from base.proxy_account_pool import AccountPool
from models import douyin
from tools import utils
from .client import DOUYINClient
from .exception import DataFetchError
from .login import DouYinLogin
class DouYinCrawler(AbstractCrawler):
platform: str
login_type: str
context_page: Page
dy_client: DOUYINClient
account_pool: AccountPool
browser_context: BrowserContext
def __init__(self) -> None:
self.browser_context: Optional[BrowserContext] = None # type: ignore
self.context_page: Optional[Page] = None # type: ignore
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"
self.command_args: Optional[Namespace] = None # type: ignore
self.account_pool: Optional[AccountPool] = None # type: ignore
def init_config(self, **kwargs):
for key, value in kwargs.items():
setattr(self, key, value)
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()
@@ -53,7 +53,7 @@ class DouYinCrawler(AbstractCrawler):
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(
login_type=self.command_args.lt, # type: ignore
login_type=self.login_type,
login_phone=account_phone,
browser_context=self.browser_context,
context_page=self.context_page,
@@ -63,25 +63,25 @@ class DouYinCrawler(AbstractCrawler):
await self.dy_client.update_cookies(browser_context=self.browser_context)
# search_posts
await self.search_posts()
await self.search()
utils.logger.info("Douyin Crawler finished ...")
async def search_posts(self) -> None:
async def search(self) -> None:
utils.logger.info("Begin search douyin keywords")
for keyword in config.KEYWORDS.split(","):
utils.logger.info(f"Current keyword: {keyword}")
aweme_list: List[str] = []
max_note_len = config.MAX_PAGE_NUM
dy_limite_count = 10 # douyin fixed limit page 10
page = 0
while max_note_len > 0:
while (page + 1) * dy_limite_count <= config.CRAWLER_MAX_NOTES_COUNT:
try:
posts_res = await self.dy_client.search_info_by_keyword(keyword=keyword, offset=page * 10)
posts_res = await self.dy_client.search_info_by_keyword(keyword=keyword,
offset=page * dy_limite_count)
except DataFetchError:
utils.logger.error(f"search douyin keyword: {keyword} failed")
break
page += 1
max_note_len -= 10
for post_item in posts_res.get("data"):
try:
aweme_info: Dict = post_item.get("aweme_info") or \
@@ -93,15 +93,15 @@ class DouYinCrawler(AbstractCrawler):
utils.logger.info(f"keyword:{keyword}, aweme_list:{aweme_list}")
await self.batch_get_note_comments(aweme_list)
async def batch_get_note_comments(self, aweme_list: List[str]):
async def batch_get_note_comments(self, aweme_list: List[str]) -> None:
task_list: List[Task] = []
_semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
for aweme_id in aweme_list:
task = asyncio.create_task(self.get_comments(aweme_id, _semaphore), name=aweme_id)
task = asyncio.create_task(self.get_comments(aweme_id, semaphore), name=aweme_id)
task_list.append(task)
await asyncio.wait(task_list)
async def get_comments(self, aweme_id: str, semaphore: "asyncio.Semaphore"):
async def get_comments(self, aweme_id: str, semaphore: asyncio.Semaphore) -> None:
async with semaphore:
try:
await self.dy_client.get_aweme_all_comments(
@@ -155,7 +155,7 @@ class DouYinCrawler(AbstractCrawler):
"""Launch browser and create browser context"""
if config.SAVE_LOGIN_STATE:
user_data_dir = os.path.join(os.getcwd(), "browser_data",
config.USER_DATA_DIR % self.command_args.platform) # type: ignore
config.USER_DATA_DIR % self.platform) # type: ignore
browser_context = await chromium.launch_persistent_context(
user_data_dir=user_data_dir,
accept_downloads=True,
@@ -173,7 +173,7 @@ class DouYinCrawler(AbstractCrawler):
)
return browser_context
async def close(self):
async def close(self) -> None:
"""Close browser context"""
await self.browser_context.close()
utils.logger.info("Browser context closed ...")