Uploading the AI Crawler System: MindSpider
This commit is contained in:
戒酒的李白
@@ -0,0 +1,13 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
from .core import KuaishouCrawler
|
||||
@@ -0,0 +1,313 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
import asyncio
|
||||
import json
|
||||
from typing import Any, Callable, Dict, List, Optional
|
||||
from urllib.parse import urlencode
|
||||
|
||||
import httpx
|
||||
from playwright.async_api import BrowserContext, Page
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractApiClient
|
||||
from tools import utils
|
||||
|
||||
from .exception import DataFetchError
|
||||
from .graphql import KuaiShouGraphQL
|
||||
|
||||
|
||||
class KuaiShouClient(AbstractApiClient):
|
||||
def __init__(
|
||||
self,
|
||||
timeout=10,
|
||||
proxy=None,
|
||||
*,
|
||||
headers: Dict[str, str],
|
||||
playwright_page: Page,
|
||||
cookie_dict: Dict[str, str],
|
||||
):
|
||||
self.proxy = proxy
|
||||
self.timeout = timeout
|
||||
self.headers = headers
|
||||
self._host = "https://www.kuaishou.com/graphql"
|
||||
self.playwright_page = playwright_page
|
||||
self.cookie_dict = cookie_dict
|
||||
self.graphql = KuaiShouGraphQL()
|
||||
|
||||
async def request(self, method, url, **kwargs) -> Any:
|
||||
async with httpx.AsyncClient(proxy=self.proxy) as client:
|
||||
response = await client.request(method, url, timeout=self.timeout, **kwargs)
|
||||
data: Dict = response.json()
|
||||
if data.get("errors"):
|
||||
raise DataFetchError(data.get("errors", "unkonw error"))
|
||||
else:
|
||||
return data.get("data", {})
|
||||
|
||||
async def get(self, uri: str, params=None) -> Dict:
|
||||
final_uri = uri
|
||||
if isinstance(params, dict):
|
||||
final_uri = f"{uri}?" f"{urlencode(params)}"
|
||||
return await self.request(
|
||||
method="GET", url=f"{self._host}{final_uri}", headers=self.headers
|
||||
)
|
||||
|
||||
async def post(self, uri: str, data: dict) -> Dict:
|
||||
json_str = json.dumps(data, separators=(",", ":"), ensure_ascii=False)
|
||||
return await self.request(
|
||||
method="POST", url=f"{self._host}{uri}", data=json_str, headers=self.headers
|
||||
)
|
||||
|
||||
async def pong(self) -> bool:
|
||||
"""get a note to check if login state is ok"""
|
||||
utils.logger.info("[KuaiShouClient.pong] Begin pong kuaishou...")
|
||||
ping_flag = False
|
||||
try:
|
||||
post_data = {
|
||||
"operationName": "visionProfileUserList",
|
||||
"variables": {
|
||||
"ftype": 1,
|
||||
},
|
||||
"query": self.graphql.get("vision_profile_user_list"),
|
||||
}
|
||||
res = await self.post("", post_data)
|
||||
if res.get("visionProfileUserList", {}).get("result") == 1:
|
||||
ping_flag = True
|
||||
except Exception as e:
|
||||
utils.logger.error(
|
||||
f"[KuaiShouClient.pong] Pong kuaishou failed: {e}, and try to login again..."
|
||||
)
|
||||
ping_flag = False
|
||||
return ping_flag
|
||||
|
||||
async def update_cookies(self, browser_context: BrowserContext):
|
||||
cookie_str, cookie_dict = utils.convert_cookies(await browser_context.cookies())
|
||||
self.headers["Cookie"] = cookie_str
|
||||
self.cookie_dict = cookie_dict
|
||||
|
||||
async def search_info_by_keyword(
|
||||
self, keyword: str, pcursor: str, search_session_id: str = ""
|
||||
):
|
||||
"""
|
||||
KuaiShou web search api
|
||||
:param keyword: search keyword
|
||||
:param pcursor: limite page curson
|
||||
:param search_session_id: search session id
|
||||
:return:
|
||||
"""
|
||||
post_data = {
|
||||
"operationName": "visionSearchPhoto",
|
||||
"variables": {
|
||||
"keyword": keyword,
|
||||
"pcursor": pcursor,
|
||||
"page": "search",
|
||||
"searchSessionId": search_session_id,
|
||||
},
|
||||
"query": self.graphql.get("search_query"),
|
||||
}
|
||||
return await self.post("", post_data)
|
||||
|
||||
async def get_video_info(self, photo_id: str) -> Dict:
|
||||
"""
|
||||
Kuaishou web video detail api
|
||||
:param photo_id:
|
||||
:return:
|
||||
"""
|
||||
post_data = {
|
||||
"operationName": "visionVideoDetail",
|
||||
"variables": {"photoId": photo_id, "page": "search"},
|
||||
"query": self.graphql.get("video_detail"),
|
||||
}
|
||||
return await self.post("", post_data)
|
||||
|
||||
async def get_video_comments(self, photo_id: str, pcursor: str = "") -> Dict:
|
||||
"""get video comments
|
||||
:param photo_id: photo id you want to fetch
|
||||
:param pcursor: last you get pcursor, defaults to ""
|
||||
:return:
|
||||
"""
|
||||
post_data = {
|
||||
"operationName": "commentListQuery",
|
||||
"variables": {"photoId": photo_id, "pcursor": pcursor},
|
||||
"query": self.graphql.get("comment_list"),
|
||||
}
|
||||
return await self.post("", post_data)
|
||||
|
||||
async def get_video_sub_comments(
|
||||
self, photo_id: str, rootCommentId: str, pcursor: str = ""
|
||||
) -> Dict:
|
||||
"""get video sub comments
|
||||
:param photo_id: photo id you want to fetch
|
||||
:param pcursor: last you get pcursor, defaults to ""
|
||||
:return:
|
||||
"""
|
||||
post_data = {
|
||||
"operationName": "visionSubCommentList",
|
||||
"variables": {
|
||||
"photoId": photo_id,
|
||||
"pcursor": pcursor,
|
||||
"rootCommentId": rootCommentId,
|
||||
},
|
||||
"query": self.graphql.get("vision_sub_comment_list"),
|
||||
}
|
||||
return await self.post("", post_data)
|
||||
|
||||
async def get_creator_profile(self, userId: str) -> Dict:
|
||||
post_data = {
|
||||
"operationName": "visionProfile",
|
||||
"variables": {"userId": userId},
|
||||
"query": self.graphql.get("vision_profile"),
|
||||
}
|
||||
return await self.post("", post_data)
|
||||
|
||||
async def get_video_by_creater(self, userId: str, pcursor: str = "") -> Dict:
|
||||
post_data = {
|
||||
"operationName": "visionProfilePhotoList",
|
||||
"variables": {"page": "profile", "pcursor": pcursor, "userId": userId},
|
||||
"query": self.graphql.get("vision_profile_photo_list"),
|
||||
}
|
||||
return await self.post("", post_data)
|
||||
|
||||
async def get_video_all_comments(
|
||||
self,
|
||||
photo_id: str,
|
||||
crawl_interval: float = 1.0,
|
||||
callback: Optional[Callable] = None,
|
||||
max_count: int = 10,
|
||||
):
|
||||
"""
|
||||
get video all comments include sub comments
|
||||
:param photo_id:
|
||||
:param crawl_interval:
|
||||
:param callback:
|
||||
:param max_count:
|
||||
:return:
|
||||
"""
|
||||
|
||||
result = []
|
||||
pcursor = ""
|
||||
|
||||
while pcursor != "no_more" and len(result) < max_count:
|
||||
comments_res = await self.get_video_comments(photo_id, pcursor)
|
||||
vision_commen_list = comments_res.get("visionCommentList", {})
|
||||
pcursor = vision_commen_list.get("pcursor", "")
|
||||
comments = vision_commen_list.get("rootComments", [])
|
||||
if len(result) + len(comments) > max_count:
|
||||
comments = comments[: max_count - len(result)]
|
||||
if callback: # 如果有回调函数，就执行回调函数
|
||||
await callback(photo_id, comments)
|
||||
result.extend(comments)
|
||||
await asyncio.sleep(crawl_interval)
|
||||
sub_comments = await self.get_comments_all_sub_comments(
|
||||
comments, photo_id, crawl_interval, callback
|
||||
)
|
||||
result.extend(sub_comments)
|
||||
return result
|
||||
|
||||
async def get_comments_all_sub_comments(
|
||||
self,
|
||||
comments: List[Dict],
|
||||
photo_id,
|
||||
crawl_interval: float = 1.0,
|
||||
callback: Optional[Callable] = None,
|
||||
) -> List[Dict]:
|
||||
"""
|
||||
获取指定一级评论下的所有二级评论, 该方法会一直查找一级评论下的所有二级评论信息
|
||||
Args:
|
||||
comments: 评论列表
|
||||
photo_id: 视频id
|
||||
crawl_interval: 爬取一次评论的延迟单位（秒）
|
||||
callback: 一次评论爬取结束后
|
||||
Returns:
|
||||
|
||||
"""
|
||||
if not config.ENABLE_GET_SUB_COMMENTS:
|
||||
utils.logger.info(
|
||||
f"[KuaiShouClient.get_comments_all_sub_comments] Crawling sub_comment mode is not enabled"
|
||||
)
|
||||
return []
|
||||
|
||||
result = []
|
||||
for comment in comments:
|
||||
sub_comments = comment.get("subComments")
|
||||
if sub_comments and callback:
|
||||
await callback(photo_id, sub_comments)
|
||||
|
||||
sub_comment_pcursor = comment.get("subCommentsPcursor")
|
||||
if sub_comment_pcursor == "no_more":
|
||||
continue
|
||||
|
||||
root_comment_id = comment.get("commentId")
|
||||
sub_comment_pcursor = ""
|
||||
|
||||
while sub_comment_pcursor != "no_more":
|
||||
comments_res = await self.get_video_sub_comments(
|
||||
photo_id, root_comment_id, sub_comment_pcursor
|
||||
)
|
||||
vision_sub_comment_list = comments_res.get("visionSubCommentList", {})
|
||||
sub_comment_pcursor = vision_sub_comment_list.get("pcursor", "no_more")
|
||||
|
||||
comments = vision_sub_comment_list.get("subComments", {})
|
||||
if callback:
|
||||
await callback(photo_id, comments)
|
||||
await asyncio.sleep(crawl_interval)
|
||||
result.extend(comments)
|
||||
return result
|
||||
|
||||
async def get_creator_info(self, user_id: str) -> Dict:
|
||||
"""
|
||||
eg: https://www.kuaishou.com/profile/3x4jtnbfter525a
|
||||
快手用户主页
|
||||
"""
|
||||
|
||||
visionProfile = await self.get_creator_profile(user_id)
|
||||
return visionProfile.get("userProfile")
|
||||
|
||||
async def get_all_videos_by_creator(
|
||||
self,
|
||||
user_id: str,
|
||||
crawl_interval: float = 1.0,
|
||||
callback: Optional[Callable] = None,
|
||||
) -> List[Dict]:
|
||||
"""
|
||||
获取指定用户下的所有发过的帖子，该方法会一直查找一个用户下的所有帖子信息
|
||||
Args:
|
||||
user_id: 用户ID
|
||||
crawl_interval: 爬取一次的延迟单位（秒）
|
||||
callback: 一次分页爬取结束后的更新回调函数
|
||||
Returns:
|
||||
|
||||
"""
|
||||
result = []
|
||||
pcursor = ""
|
||||
|
||||
while pcursor != "no_more":
|
||||
videos_res = await self.get_video_by_creater(user_id, pcursor)
|
||||
if not videos_res:
|
||||
utils.logger.error(
|
||||
f"[KuaiShouClient.get_all_videos_by_creator] The current creator may have been banned by ks, so they cannot access the data."
|
||||
)
|
||||
break
|
||||
|
||||
vision_profile_photo_list = videos_res.get("visionProfilePhotoList", {})
|
||||
pcursor = vision_profile_photo_list.get("pcursor", "")
|
||||
|
||||
videos = vision_profile_photo_list.get("feeds", [])
|
||||
utils.logger.info(
|
||||
f"[KuaiShouClient.get_all_videos_by_creator] got user_id:{user_id} videos len : {len(videos)}"
|
||||
)
|
||||
|
||||
if callback:
|
||||
await callback(videos)
|
||||
await asyncio.sleep(crawl_interval)
|
||||
result.extend(videos)
|
||||
return result
|
||||
@@ -0,0 +1,396 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import random
|
||||
import time
|
||||
from asyncio import Task
|
||||
from typing import Dict, List, Optional, Tuple
|
||||
|
||||
from playwright.async_api import (
|
||||
BrowserContext,
|
||||
BrowserType,
|
||||
Page,
|
||||
Playwright,
|
||||
async_playwright,
|
||||
)
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractCrawler
|
||||
from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
|
||||
from store import kuaishou as kuaishou_store
|
||||
from tools import utils
|
||||
from tools.cdp_browser import CDPBrowserManager
|
||||
from var import comment_tasks_var, crawler_type_var, source_keyword_var
|
||||
|
||||
from .client import KuaiShouClient
|
||||
from .exception import DataFetchError
|
||||
from .login import KuaishouLogin
|
||||
|
||||
|
||||
class KuaishouCrawler(AbstractCrawler):
|
||||
context_page: Page
|
||||
ks_client: KuaiShouClient
|
||||
browser_context: BrowserContext
|
||||
cdp_manager: Optional[CDPBrowserManager]
|
||||
|
||||
def __init__(self):
|
||||
self.index_url = "https://www.kuaishou.com"
|
||||
self.user_agent = utils.get_user_agent()
|
||||
self.cdp_manager = None
|
||||
|
||||
async def start(self):
|
||||
playwright_proxy_format, httpx_proxy_format = None, None
|
||||
if config.ENABLE_IP_PROXY:
|
||||
ip_proxy_pool = await create_ip_pool(
|
||||
config.IP_PROXY_POOL_COUNT, enable_validate_ip=True
|
||||
)
|
||||
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
|
||||
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(
|
||||
ip_proxy_info
|
||||
)
|
||||
|
||||
async with async_playwright() as playwright:
|
||||
# 根据配置选择启动模式
|
||||
if config.ENABLE_CDP_MODE:
|
||||
utils.logger.info("[KuaishouCrawler] 使用CDP模式启动浏览器")
|
||||
self.browser_context = await self.launch_browser_with_cdp(
|
||||
playwright,
|
||||
playwright_proxy_format,
|
||||
self.user_agent,
|
||||
headless=config.CDP_HEADLESS,
|
||||
)
|
||||
else:
|
||||
utils.logger.info("[KuaishouCrawler] 使用标准模式启动浏览器")
|
||||
# Launch a browser context.
|
||||
chromium = playwright.chromium
|
||||
self.browser_context = await self.launch_browser(
|
||||
chromium, None, 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(f"{self.index_url}?isHome=1")
|
||||
|
||||
# Create a client to interact with the kuaishou website.
|
||||
self.ks_client = await self.create_ks_client(httpx_proxy_format)
|
||||
if not await self.ks_client.pong():
|
||||
login_obj = KuaishouLogin(
|
||||
login_type=config.LOGIN_TYPE,
|
||||
login_phone=httpx_proxy_format,
|
||||
browser_context=self.browser_context,
|
||||
context_page=self.context_page,
|
||||
cookie_str=config.COOKIES,
|
||||
)
|
||||
await login_obj.begin()
|
||||
await self.ks_client.update_cookies(
|
||||
browser_context=self.browser_context
|
||||
)
|
||||
|
||||
crawler_type_var.set(config.CRAWLER_TYPE)
|
||||
if config.CRAWLER_TYPE == "search":
|
||||
# Search for videos and retrieve their comment information.
|
||||
await self.search()
|
||||
elif config.CRAWLER_TYPE == "detail":
|
||||
# Get the information and comments of the specified post
|
||||
await self.get_specified_videos()
|
||||
elif config.CRAWLER_TYPE == "creator":
|
||||
# Get creator's information and their videos and comments
|
||||
await self.get_creators_and_videos()
|
||||
else:
|
||||
pass
|
||||
|
||||
utils.logger.info("[KuaishouCrawler.start] Kuaishou Crawler finished ...")
|
||||
|
||||
async def search(self):
|
||||
utils.logger.info("[KuaishouCrawler.search] Begin search kuaishou keywords")
|
||||
ks_limit_count = 20 # kuaishou limit page fixed value
|
||||
if config.CRAWLER_MAX_NOTES_COUNT < ks_limit_count:
|
||||
config.CRAWLER_MAX_NOTES_COUNT = ks_limit_count
|
||||
start_page = config.START_PAGE
|
||||
for keyword in config.KEYWORDS.split(","):
|
||||
search_session_id = ""
|
||||
source_keyword_var.set(keyword)
|
||||
utils.logger.info(
|
||||
f"[KuaishouCrawler.search] Current search keyword: {keyword}"
|
||||
)
|
||||
page = 1
|
||||
while (
|
||||
page - start_page + 1
|
||||
) * ks_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
|
||||
if page < start_page:
|
||||
utils.logger.info(f"[KuaishouCrawler.search] Skip page: {page}")
|
||||
page += 1
|
||||
continue
|
||||
utils.logger.info(
|
||||
f"[KuaishouCrawler.search] search kuaishou keyword: {keyword}, page: {page}"
|
||||
)
|
||||
video_id_list: List[str] = []
|
||||
videos_res = await self.ks_client.search_info_by_keyword(
|
||||
keyword=keyword,
|
||||
pcursor=str(page),
|
||||
search_session_id=search_session_id,
|
||||
)
|
||||
if not videos_res:
|
||||
utils.logger.error(
|
||||
f"[KuaishouCrawler.search] search info by keyword:{keyword} not found data"
|
||||
)
|
||||
continue
|
||||
|
||||
vision_search_photo: Dict = videos_res.get("visionSearchPhoto")
|
||||
if vision_search_photo.get("result") != 1:
|
||||
utils.logger.error(
|
||||
f"[KuaishouCrawler.search] search info by keyword:{keyword} not found data "
|
||||
)
|
||||
continue
|
||||
search_session_id = vision_search_photo.get("searchSessionId", "")
|
||||
for video_detail in vision_search_photo.get("feeds"):
|
||||
video_id_list.append(video_detail.get("photo", {}).get("id"))
|
||||
await kuaishou_store.update_kuaishou_video(video_item=video_detail)
|
||||
|
||||
# batch fetch video comments
|
||||
page += 1
|
||||
await self.batch_get_video_comments(video_id_list)
|
||||
|
||||
async def get_specified_videos(self):
|
||||
"""Get the information and comments of the specified post"""
|
||||
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
|
||||
task_list = [
|
||||
self.get_video_info_task(video_id=video_id, semaphore=semaphore)
|
||||
for video_id in config.KS_SPECIFIED_ID_LIST
|
||||
]
|
||||
video_details = await asyncio.gather(*task_list)
|
||||
for video_detail in video_details:
|
||||
if video_detail is not None:
|
||||
await kuaishou_store.update_kuaishou_video(video_detail)
|
||||
await self.batch_get_video_comments(config.KS_SPECIFIED_ID_LIST)
|
||||
|
||||
async def get_video_info_task(
|
||||
self, video_id: str, semaphore: asyncio.Semaphore
|
||||
) -> Optional[Dict]:
|
||||
"""Get video detail task"""
|
||||
async with semaphore:
|
||||
try:
|
||||
result = await self.ks_client.get_video_info(video_id)
|
||||
utils.logger.info(
|
||||
f"[KuaishouCrawler.get_video_info_task] Get video_id:{video_id} info result: {result} ..."
|
||||
)
|
||||
return result.get("visionVideoDetail")
|
||||
except DataFetchError as ex:
|
||||
utils.logger.error(
|
||||
f"[KuaishouCrawler.get_video_info_task] Get video detail error: {ex}"
|
||||
)
|
||||
return None
|
||||
except KeyError as ex:
|
||||
utils.logger.error(
|
||||
f"[KuaishouCrawler.get_video_info_task] have not fund video detail video_id:{video_id}, err: {ex}"
|
||||
)
|
||||
return None
|
||||
|
||||
async def batch_get_video_comments(self, video_id_list: List[str]):
|
||||
"""
|
||||
batch get video comments
|
||||
:param video_id_list:
|
||||
:return:
|
||||
"""
|
||||
if not config.ENABLE_GET_COMMENTS:
|
||||
utils.logger.info(
|
||||
f"[KuaishouCrawler.batch_get_video_comments] Crawling comment mode is not enabled"
|
||||
)
|
||||
return
|
||||
|
||||
utils.logger.info(
|
||||
f"[KuaishouCrawler.batch_get_video_comments] video ids:{video_id_list}"
|
||||
)
|
||||
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
|
||||
task_list: List[Task] = []
|
||||
for video_id in video_id_list:
|
||||
task = asyncio.create_task(
|
||||
self.get_comments(video_id, semaphore), name=video_id
|
||||
)
|
||||
task_list.append(task)
|
||||
|
||||
comment_tasks_var.set(task_list)
|
||||
await asyncio.gather(*task_list)
|
||||
|
||||
async def get_comments(self, video_id: str, semaphore: asyncio.Semaphore):
|
||||
"""
|
||||
get comment for video id
|
||||
:param video_id:
|
||||
:param semaphore:
|
||||
:return:
|
||||
"""
|
||||
async with semaphore:
|
||||
try:
|
||||
utils.logger.info(
|
||||
f"[KuaishouCrawler.get_comments] begin get video_id: {video_id} comments ..."
|
||||
)
|
||||
await self.ks_client.get_video_all_comments(
|
||||
photo_id=video_id,
|
||||
crawl_interval=random.random(),
|
||||
callback=kuaishou_store.batch_update_ks_video_comments,
|
||||
max_count=config.CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES,
|
||||
)
|
||||
except DataFetchError as ex:
|
||||
utils.logger.error(
|
||||
f"[KuaishouCrawler.get_comments] get video_id: {video_id} comment error: {ex}"
|
||||
)
|
||||
except Exception as e:
|
||||
utils.logger.error(
|
||||
f"[KuaishouCrawler.get_comments] may be been blocked, err:{e}"
|
||||
)
|
||||
# use time.sleeep block main coroutine instead of asyncio.sleep and cacel running comment task
|
||||
# maybe kuaishou block our request, we will take a nap and update the cookie again
|
||||
current_running_tasks = comment_tasks_var.get()
|
||||
for task in current_running_tasks:
|
||||
task.cancel()
|
||||
time.sleep(20)
|
||||
await self.context_page.goto(f"{self.index_url}?isHome=1")
|
||||
await self.ks_client.update_cookies(
|
||||
browser_context=self.browser_context
|
||||
)
|
||||
|
||||
async def create_ks_client(self, httpx_proxy: Optional[str]) -> KuaiShouClient:
|
||||
"""Create ks client"""
|
||||
utils.logger.info(
|
||||
"[KuaishouCrawler.create_ks_client] Begin create kuaishou API client ..."
|
||||
)
|
||||
cookie_str, cookie_dict = utils.convert_cookies(
|
||||
await self.browser_context.cookies()
|
||||
)
|
||||
ks_client_obj = KuaiShouClient(
|
||||
proxy=httpx_proxy,
|
||||
headers={
|
||||
"User-Agent": self.user_agent,
|
||||
"Cookie": cookie_str,
|
||||
"Origin": self.index_url,
|
||||
"Referer": self.index_url,
|
||||
"Content-Type": "application/json;charset=UTF-8",
|
||||
},
|
||||
playwright_page=self.context_page,
|
||||
cookie_dict=cookie_dict,
|
||||
)
|
||||
return ks_client_obj
|
||||
|
||||
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"""
|
||||
utils.logger.info(
|
||||
"[KuaishouCrawler.launch_browser] Begin create browser context ..."
|
||||
)
|
||||
if config.SAVE_LOGIN_STATE:
|
||||
user_data_dir = os.path.join(
|
||||
os.getcwd(), "browser_data", config.USER_DATA_DIR % config.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,
|
||||
)
|
||||
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
|
||||
|
||||
async def launch_browser_with_cdp(
|
||||
self,
|
||||
playwright: Playwright,
|
||||
playwright_proxy: Optional[Dict],
|
||||
user_agent: Optional[str],
|
||||
headless: bool = True,
|
||||
) -> BrowserContext:
|
||||
"""
|
||||
使用CDP模式启动浏览器
|
||||
"""
|
||||
try:
|
||||
self.cdp_manager = CDPBrowserManager()
|
||||
browser_context = await self.cdp_manager.launch_and_connect(
|
||||
playwright=playwright,
|
||||
playwright_proxy=playwright_proxy,
|
||||
user_agent=user_agent,
|
||||
headless=headless,
|
||||
)
|
||||
|
||||
# 显示浏览器信息
|
||||
browser_info = await self.cdp_manager.get_browser_info()
|
||||
utils.logger.info(f"[KuaishouCrawler] CDP浏览器信息: {browser_info}")
|
||||
|
||||
return browser_context
|
||||
|
||||
except Exception as e:
|
||||
utils.logger.error(
|
||||
f"[KuaishouCrawler] CDP模式启动失败，回退到标准模式: {e}"
|
||||
)
|
||||
# 回退到标准模式
|
||||
chromium = playwright.chromium
|
||||
return await self.launch_browser(
|
||||
chromium, playwright_proxy, user_agent, headless
|
||||
)
|
||||
|
||||
async def get_creators_and_videos(self) -> None:
|
||||
"""Get creator's videos and retrieve their comment information."""
|
||||
utils.logger.info(
|
||||
"[KuaiShouCrawler.get_creators_and_videos] Begin get kuaishou creators"
|
||||
)
|
||||
for user_id in config.KS_CREATOR_ID_LIST:
|
||||
# get creator detail info from web html content
|
||||
createor_info: Dict = await self.ks_client.get_creator_info(user_id=user_id)
|
||||
if createor_info:
|
||||
await kuaishou_store.save_creator(user_id, creator=createor_info)
|
||||
|
||||
# Get all video information of the creator
|
||||
all_video_list = await self.ks_client.get_all_videos_by_creator(
|
||||
user_id=user_id,
|
||||
crawl_interval=random.random(),
|
||||
callback=self.fetch_creator_video_detail,
|
||||
)
|
||||
|
||||
video_ids = [
|
||||
video_item.get("photo", {}).get("id") for video_item in all_video_list
|
||||
]
|
||||
await self.batch_get_video_comments(video_ids)
|
||||
|
||||
async def fetch_creator_video_detail(self, video_list: List[Dict]):
|
||||
"""
|
||||
Concurrently obtain the specified post list and save the data
|
||||
"""
|
||||
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
|
||||
task_list = [
|
||||
self.get_video_info_task(post_item.get("photo", {}).get("id"), semaphore)
|
||||
for post_item in video_list
|
||||
]
|
||||
|
||||
video_details = await asyncio.gather(*task_list)
|
||||
for video_detail in video_details:
|
||||
if video_detail is not None:
|
||||
await kuaishou_store.update_kuaishou_video(video_detail)
|
||||
|
||||
async def close(self):
|
||||
"""Close browser context"""
|
||||
# 如果使用CDP模式，需要特殊处理
|
||||
if self.cdp_manager:
|
||||
await self.cdp_manager.cleanup()
|
||||
self.cdp_manager = None
|
||||
else:
|
||||
await self.browser_context.close()
|
||||
utils.logger.info("[KuaishouCrawler.close] Browser context closed ...")
|
||||
@@ -0,0 +1,20 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
from httpx import RequestError
|
||||
|
||||
|
||||
class DataFetchError(RequestError):
|
||||
"""something error when fetch"""
|
||||
|
||||
|
||||
class IPBlockError(RequestError):
|
||||
"""fetch so fast that the server block us ip"""
|
||||
@@ -0,0 +1,12 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
@@ -0,0 +1,33 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
# 快手的数据传输是基于GraphQL实现的
|
||||
# 这个类负责获取一些GraphQL的schema
|
||||
from typing import Dict
|
||||
|
||||
|
||||
class KuaiShouGraphQL:
|
||||
graphql_queries: Dict[str, str]= {}
|
||||
|
||||
def __init__(self):
|
||||
self.graphql_dir = "media_platform/kuaishou/graphql/"
|
||||
self.load_graphql_queries()
|
||||
|
||||
def load_graphql_queries(self):
|
||||
graphql_files = ["search_query.graphql", "video_detail.graphql", "comment_list.graphql", "vision_profile.graphql","vision_profile_photo_list.graphql","vision_profile_user_list.graphql","vision_sub_comment_list.graphql"]
|
||||
|
||||
for file in graphql_files:
|
||||
with open(self.graphql_dir + file, mode="r") as f:
|
||||
query_name = file.split(".")[0]
|
||||
self.graphql_queries[query_name] = f.read()
|
||||
|
||||
def get(self, query_name: str) -> str:
|
||||
return self.graphql_queries.get(query_name, "Query not found")
|
||||
+39
@@ -0,0 +1,39 @@
|
||||
query commentListQuery($photoId: String, $pcursor: String) {
|
||||
visionCommentList(photoId: $photoId, pcursor: $pcursor) {
|
||||
commentCount
|
||||
pcursor
|
||||
rootComments {
|
||||
commentId
|
||||
authorId
|
||||
authorName
|
||||
content
|
||||
headurl
|
||||
timestamp
|
||||
likedCount
|
||||
realLikedCount
|
||||
liked
|
||||
status
|
||||
authorLiked
|
||||
subCommentCount
|
||||
subCommentsPcursor
|
||||
subComments {
|
||||
commentId
|
||||
authorId
|
||||
authorName
|
||||
content
|
||||
headurl
|
||||
timestamp
|
||||
likedCount
|
||||
realLikedCount
|
||||
liked
|
||||
status
|
||||
authorLiked
|
||||
replyToUserName
|
||||
replyTo
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
}
|
||||
+111
@@ -0,0 +1,111 @@
|
||||
fragment photoContent on PhotoEntity {
|
||||
__typename
|
||||
id
|
||||
duration
|
||||
caption
|
||||
originCaption
|
||||
likeCount
|
||||
viewCount
|
||||
commentCount
|
||||
realLikeCount
|
||||
coverUrl
|
||||
photoUrl
|
||||
photoH265Url
|
||||
manifest
|
||||
manifestH265
|
||||
videoResource
|
||||
coverUrls {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
timestamp
|
||||
expTag
|
||||
animatedCoverUrl
|
||||
distance
|
||||
videoRatio
|
||||
liked
|
||||
stereoType
|
||||
profileUserTopPhoto
|
||||
musicBlocked
|
||||
}
|
||||
|
||||
fragment recoPhotoFragment on recoPhotoEntity {
|
||||
__typename
|
||||
id
|
||||
duration
|
||||
caption
|
||||
originCaption
|
||||
likeCount
|
||||
viewCount
|
||||
commentCount
|
||||
realLikeCount
|
||||
coverUrl
|
||||
photoUrl
|
||||
photoH265Url
|
||||
manifest
|
||||
manifestH265
|
||||
videoResource
|
||||
coverUrls {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
timestamp
|
||||
expTag
|
||||
animatedCoverUrl
|
||||
distance
|
||||
videoRatio
|
||||
liked
|
||||
stereoType
|
||||
profileUserTopPhoto
|
||||
musicBlocked
|
||||
}
|
||||
|
||||
fragment feedContent on Feed {
|
||||
type
|
||||
author {
|
||||
id
|
||||
name
|
||||
headerUrl
|
||||
following
|
||||
headerUrls {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
photo {
|
||||
...photoContent
|
||||
...recoPhotoFragment
|
||||
__typename
|
||||
}
|
||||
canAddComment
|
||||
llsid
|
||||
status
|
||||
currentPcursor
|
||||
tags {
|
||||
type
|
||||
name
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
|
||||
query visionSearchPhoto($keyword: String, $pcursor: String, $searchSessionId: String, $page: String, $webPageArea: String) {
|
||||
visionSearchPhoto(keyword: $keyword, pcursor: $pcursor, searchSessionId: $searchSessionId, page: $page, webPageArea: $webPageArea) {
|
||||
result
|
||||
llsid
|
||||
webPageArea
|
||||
feeds {
|
||||
...feedContent
|
||||
__typename
|
||||
}
|
||||
searchSessionId
|
||||
pcursor
|
||||
aladdinBanner {
|
||||
imgUrl
|
||||
link
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
}
|
||||
+80
@@ -0,0 +1,80 @@
|
||||
query visionVideoDetail($photoId: String, $type: String, $page: String, $webPageArea: String) {
|
||||
visionVideoDetail(photoId: $photoId, type: $type, page: $page, webPageArea: $webPageArea) {
|
||||
status
|
||||
type
|
||||
author {
|
||||
id
|
||||
name
|
||||
following
|
||||
headerUrl
|
||||
__typename
|
||||
}
|
||||
photo {
|
||||
id
|
||||
duration
|
||||
caption
|
||||
likeCount
|
||||
realLikeCount
|
||||
coverUrl
|
||||
photoUrl
|
||||
liked
|
||||
timestamp
|
||||
expTag
|
||||
llsid
|
||||
viewCount
|
||||
videoRatio
|
||||
stereoType
|
||||
musicBlocked
|
||||
manifest {
|
||||
mediaType
|
||||
businessType
|
||||
version
|
||||
adaptationSet {
|
||||
id
|
||||
duration
|
||||
representation {
|
||||
id
|
||||
defaultSelect
|
||||
backupUrl
|
||||
codecs
|
||||
url
|
||||
height
|
||||
width
|
||||
avgBitrate
|
||||
maxBitrate
|
||||
m3u8Slice
|
||||
qualityType
|
||||
qualityLabel
|
||||
frameRate
|
||||
featureP2sp
|
||||
hidden
|
||||
disableAdaptive
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
manifestH265
|
||||
photoH265Url
|
||||
coronaCropManifest
|
||||
coronaCropManifestH265
|
||||
croppedPhotoH265Url
|
||||
croppedPhotoUrl
|
||||
videoResource
|
||||
__typename
|
||||
}
|
||||
tags {
|
||||
type
|
||||
name
|
||||
__typename
|
||||
}
|
||||
commentLimit {
|
||||
canAddComment
|
||||
__typename
|
||||
}
|
||||
llsid
|
||||
danmakuSwitch
|
||||
__typename
|
||||
}
|
||||
}
|
||||
+27
@@ -0,0 +1,27 @@
|
||||
query visionProfile($userId: String) {
|
||||
visionProfile(userId: $userId) {
|
||||
result
|
||||
hostName
|
||||
userProfile {
|
||||
ownerCount {
|
||||
fan
|
||||
photo
|
||||
follow
|
||||
photo_public
|
||||
__typename
|
||||
}
|
||||
profile {
|
||||
gender
|
||||
user_name
|
||||
user_id
|
||||
headurl
|
||||
user_text
|
||||
user_profile_bg_url
|
||||
__typename
|
||||
}
|
||||
isFollowing
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
}
|
||||
+110
@@ -0,0 +1,110 @@
|
||||
fragment photoContent on PhotoEntity {
|
||||
__typename
|
||||
id
|
||||
duration
|
||||
caption
|
||||
originCaption
|
||||
likeCount
|
||||
viewCount
|
||||
commentCount
|
||||
realLikeCount
|
||||
coverUrl
|
||||
photoUrl
|
||||
photoH265Url
|
||||
manifest
|
||||
manifestH265
|
||||
videoResource
|
||||
coverUrls {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
timestamp
|
||||
expTag
|
||||
animatedCoverUrl
|
||||
distance
|
||||
videoRatio
|
||||
liked
|
||||
stereoType
|
||||
profileUserTopPhoto
|
||||
musicBlocked
|
||||
riskTagContent
|
||||
riskTagUrl
|
||||
}
|
||||
|
||||
fragment recoPhotoFragment on recoPhotoEntity {
|
||||
__typename
|
||||
id
|
||||
duration
|
||||
caption
|
||||
originCaption
|
||||
likeCount
|
||||
viewCount
|
||||
commentCount
|
||||
realLikeCount
|
||||
coverUrl
|
||||
photoUrl
|
||||
photoH265Url
|
||||
manifest
|
||||
manifestH265
|
||||
videoResource
|
||||
coverUrls {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
timestamp
|
||||
expTag
|
||||
animatedCoverUrl
|
||||
distance
|
||||
videoRatio
|
||||
liked
|
||||
stereoType
|
||||
profileUserTopPhoto
|
||||
musicBlocked
|
||||
riskTagContent
|
||||
riskTagUrl
|
||||
}
|
||||
|
||||
fragment feedContent on Feed {
|
||||
type
|
||||
author {
|
||||
id
|
||||
name
|
||||
headerUrl
|
||||
following
|
||||
headerUrls {
|
||||
url
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
photo {
|
||||
...photoContent
|
||||
...recoPhotoFragment
|
||||
__typename
|
||||
}
|
||||
canAddComment
|
||||
llsid
|
||||
status
|
||||
currentPcursor
|
||||
tags {
|
||||
type
|
||||
name
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
|
||||
query visionProfilePhotoList($pcursor: String, $userId: String, $page: String, $webPageArea: String) {
|
||||
visionProfilePhotoList(pcursor: $pcursor, userId: $userId, page: $page, webPageArea: $webPageArea) {
|
||||
result
|
||||
llsid
|
||||
webPageArea
|
||||
feeds {
|
||||
...feedContent
|
||||
__typename
|
||||
}
|
||||
hostName
|
||||
pcursor
|
||||
__typename
|
||||
}
|
||||
}
|
||||
+16
@@ -0,0 +1,16 @@
|
||||
query visionProfileUserList($pcursor: String, $ftype: Int) {
|
||||
visionProfileUserList(pcursor: $pcursor, ftype: $ftype) {
|
||||
result
|
||||
fols {
|
||||
user_name
|
||||
headurl
|
||||
user_text
|
||||
isFollowing
|
||||
user_id
|
||||
__typename
|
||||
}
|
||||
hostName
|
||||
pcursor
|
||||
__typename
|
||||
}
|
||||
}
|
||||
+22
@@ -0,0 +1,22 @@
|
||||
mutation visionSubCommentList($photoId: String, $rootCommentId: String, $pcursor: String) {
|
||||
visionSubCommentList(photoId: $photoId, rootCommentId: $rootCommentId, pcursor: $pcursor) {
|
||||
pcursor
|
||||
subComments {
|
||||
commentId
|
||||
authorId
|
||||
authorName
|
||||
content
|
||||
headurl
|
||||
timestamp
|
||||
likedCount
|
||||
realLikedCount
|
||||
liked
|
||||
status
|
||||
authorLiked
|
||||
replyToUserName
|
||||
replyTo
|
||||
__typename
|
||||
}
|
||||
__typename
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,113 @@
|
||||
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
|
||||
# 1. 不得用于任何商业用途。
|
||||
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
|
||||
# 3. 不得进行大规模爬取或对平台造成运营干扰。
|
||||
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
|
||||
# 5. 不得用于任何非法或不当的用途。
|
||||
#
|
||||
# 详细许可条款请参阅项目根目录下的LICENSE文件。
|
||||
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
|
||||
|
||||
|
||||
import asyncio
|
||||
import functools
|
||||
import sys
|
||||
from typing import Optional
|
||||
|
||||
from playwright.async_api import BrowserContext, Page
|
||||
from tenacity import (RetryError, retry, retry_if_result, stop_after_attempt,
|
||||
wait_fixed)
|
||||
|
||||
import config
|
||||
from base.base_crawler import AbstractLogin
|
||||
from tools import utils
|
||||
|
||||
|
||||
class KuaishouLogin(AbstractLogin):
|
||||
def __init__(self,
|
||||
login_type: str,
|
||||
browser_context: BrowserContext,
|
||||
context_page: Page,
|
||||
login_phone: Optional[str] = "",
|
||||
cookie_str: str = ""
|
||||
):
|
||||
config.LOGIN_TYPE = login_type
|
||||
self.browser_context = browser_context
|
||||
self.context_page = context_page
|
||||
self.login_phone = login_phone
|
||||
self.cookie_str = cookie_str
|
||||
|
||||
async def begin(self):
|
||||
"""Start login xiaohongshu"""
|
||||
utils.logger.info("[KuaishouLogin.begin] Begin login kuaishou ...")
|
||||
if config.LOGIN_TYPE == "qrcode":
|
||||
await self.login_by_qrcode()
|
||||
elif config.LOGIN_TYPE == "phone":
|
||||
await self.login_by_mobile()
|
||||
elif config.LOGIN_TYPE == "cookie":
|
||||
await self.login_by_cookies()
|
||||
else:
|
||||
raise ValueError("[KuaishouLogin.begin] Invalid Login Type Currently only supported qrcode or phone or cookie ...")
|
||||
|
||||
@retry(stop=stop_after_attempt(600), wait=wait_fixed(1), retry=retry_if_result(lambda value: value is False))
|
||||
async def check_login_state(self) -> bool:
|
||||
"""
|
||||
Check if the current login status is successful and return True otherwise return False
|
||||
retry decorator will retry 20 times if the return value is False, and the retry interval is 1 second
|
||||
if max retry times reached, raise RetryError
|
||||
"""
|
||||
current_cookie = await self.browser_context.cookies()
|
||||
_, cookie_dict = utils.convert_cookies(current_cookie)
|
||||
kuaishou_pass_token = cookie_dict.get("passToken")
|
||||
if kuaishou_pass_token:
|
||||
return True
|
||||
return False
|
||||
|
||||
async def login_by_qrcode(self):
|
||||
"""login kuaishou website and keep webdriver login state"""
|
||||
utils.logger.info("[KuaishouLogin.login_by_qrcode] Begin login kuaishou by qrcode ...")
|
||||
|
||||
# click login button
|
||||
login_button_ele = self.context_page.locator(
|
||||
"xpath=//p[text()='登录']"
|
||||
)
|
||||
await login_button_ele.click()
|
||||
|
||||
# find login qrcode
|
||||
qrcode_img_selector = "//div[@class='qrcode-img']//img"
|
||||
base64_qrcode_img = await utils.find_login_qrcode(
|
||||
self.context_page,
|
||||
selector=qrcode_img_selector
|
||||
)
|
||||
if not base64_qrcode_img:
|
||||
utils.logger.info("[KuaishouLogin.login_by_qrcode] login failed , have not found qrcode please check ....")
|
||||
sys.exit()
|
||||
|
||||
|
||||
# show login qrcode
|
||||
partial_show_qrcode = functools.partial(utils.show_qrcode, base64_qrcode_img)
|
||||
asyncio.get_running_loop().run_in_executor(executor=None, func=partial_show_qrcode)
|
||||
|
||||
utils.logger.info(f"[KuaishouLogin.login_by_qrcode] waiting for scan code login, remaining time is 20s")
|
||||
try:
|
||||
await self.check_login_state()
|
||||
except RetryError:
|
||||
utils.logger.info("[KuaishouLogin.login_by_qrcode] Login kuaishou failed by qrcode login method ...")
|
||||
sys.exit()
|
||||
|
||||
wait_redirect_seconds = 5
|
||||
utils.logger.info(f"[KuaishouLogin.login_by_qrcode] Login successful then wait for {wait_redirect_seconds} seconds redirect ...")
|
||||
await asyncio.sleep(wait_redirect_seconds)
|
||||
|
||||
async def login_by_mobile(self):
|
||||
pass
|
||||
|
||||
async def login_by_cookies(self):
|
||||
utils.logger.info("[KuaishouLogin.login_by_cookies] Begin login kuaishou by cookie ...")
|
||||
for key, value in utils.convert_str_cookie_to_dict(self.cookie_str).items():
|
||||
await self.browser_context.add_cookies([{
|
||||
'name': key,
|
||||
'value': value,
|
||||
'domain': ".kuaishou.com",
|
||||
'path': "/"
|
||||
}])
|
||||
Reference in New Issue
Block a user