Merge branch 'kuaishou'

This commit is contained in:
HIRO 2024-06-13 14:54:01 +08:00
commit fd7407cc29
12 changed files with 402 additions and 30 deletions

View File

@ -22,12 +22,11 @@
|-----|-------|----------|-----|--------|-------|-------|-------|
| 小红书 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| 抖音 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| 快手 | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ |
| 快手 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| B 站 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
| 微博 | ✅ | ✅ | ❌ | ❌ | ✅ | ✅ | ✅ |
## 使用方法
### 创建并激活 python 虚拟环境

View File

@ -103,6 +103,13 @@ BILI_CREATOR_ID_LIST = [
# ........................
]
# 指定快手创作者ID列表
KS_CREATOR_ID_LIST = [
"3x4sm73aye7jq7i",
# ........................
]
#词云相关
#是否开启生成评论词云图
ENABLE_GET_WORDCLOUD = False
@ -118,5 +125,3 @@ STOP_WORDS_FILE = "./docs/hit_stopwords.txt"
#中文字体文件路径
FONT_PATH= "./docs/STZHONGS.TTF"

View File

@ -1,7 +1,7 @@
# -*- coding: utf-8 -*-
import asyncio
import json
from typing import Any, Callable, Dict, Optional
from typing import Any, Callable, Dict, List, Optional
from urllib.parse import urlencode
import httpx
@ -67,7 +67,7 @@ class KuaiShouClient(AbstractApiClient):
"variables": {
"ftype": 1,
},
"query": self.graphql.get("vision_profile")
"query": self.graphql.get("vision_profile_user_list")
}
res = await self.post("", post_data)
if res.get("visionProfileUserList", {}).get("result") == 1:
@ -129,17 +129,60 @@ class KuaiShouClient(AbstractApiClient):
"pcursor": pcursor
},
"query": self.graphql.get("comment_list")
}
return await self.post("", post_data)
async def get_video_all_comments(self, photo_id: str, crawl_interval: float = 1.0, is_fetch_sub_comments=False,
callback: Optional[Callable] = None):
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,
):
"""
get video all comments include sub comments
:param photo_id:
:param crawl_interval:
:param is_fetch_sub_comments:
:param callback:
:return:
"""
@ -158,7 +201,106 @@ class KuaiShouClient(AbstractApiClient):
result.extend(comments)
await asyncio.sleep(crawl_interval)
if not is_fetch_sub_comments:
continue
# todo handle get sub comments
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
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
)
sub_comment_pcursor = comments_res.get("pcursor", "no_more")
comments = comments_res.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
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

View File

@ -65,11 +65,14 @@ class KuaishouCrawler(AbstractCrawler):
crawler_type_var.set(config.CRAWLER_TYPE)
if config.CRAWLER_TYPE == "search":
# Search for notes and retrieve their comment information.
# 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
@ -135,7 +138,7 @@ class KuaishouCrawler(AbstractCrawler):
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 note detail video_id:{video_id}, err: {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]):
@ -145,7 +148,7 @@ class KuaishouCrawler(AbstractCrawler):
:return:
"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[KuaishouCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
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}")
@ -200,10 +203,10 @@ class KuaishouCrawler(AbstractCrawler):
return playwright_proxy, httpx_proxy
async def create_ks_client(self, httpx_proxy: Optional[str]) -> KuaiShouClient:
"""Create xhs client"""
"""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())
xhs_client_obj = KuaiShouClient(
ks_client_obj = KuaiShouClient(
proxies=httpx_proxy,
headers={
"User-Agent": self.user_agent,
@ -215,7 +218,7 @@ class KuaishouCrawler(AbstractCrawler):
playwright_page=self.context_page,
cookie_dict=cookie_dict,
)
return xhs_client_obj
return ks_client_obj
async def launch_browser(
self,
@ -246,6 +249,39 @@ class KuaishouCrawler(AbstractCrawler):
)
return browser_context
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"""
await self.browser_context.close()

View File

@ -11,7 +11,7 @@ class KuaiShouGraphQL:
self.load_graphql_queries()
def load_graphql_queries(self):
graphql_files = ["search_query.graphql", "video_detail.graphql", "comment_list.graphql", "vision_profile.graphql"]
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:

View File

@ -1,16 +1,27 @@
query visionProfileUserList($pcursor: String, $ftype: Int) {
visionProfileUserList(pcursor: $pcursor, ftype: $ftype) {
query visionProfile($userId: String) {
visionProfile(userId: $userId) {
result
fols {
hostName
userProfile {
ownerCount {
fan
photo
follow
photo_public
__typename
}
profile {
gender
user_name
user_id
headurl
user_text
user_profile_bg_url
__typename
}
isFollowing
user_id
__typename
}
hostName
pcursor
__typename
}
}

View File

@ -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
}
}

View File

@ -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
}
}

View File

@ -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
}
}

View File

@ -8,6 +8,7 @@ from tenacity import (RetryError, retry, retry_if_result, stop_after_attempt,
wait_fixed)
from base.base_crawler import AbstractLogin
import config
from tools import utils

View File

@ -76,3 +76,22 @@ async def update_ks_video_comment(video_id: str, comment_item: Dict):
utils.logger.info(
f"[store.kuaishou.update_ks_video_comment] Kuaishou video comment: {comment_id}, content: {save_comment_item.get('content')}")
await KuaishouStoreFactory.create_store().store_comment(comment_item=save_comment_item)
async def save_creator(user_id: str, creator: Dict):
ownerCount = creator.get('ownerCount', {})
profile = creator.get('profile', {})
local_db_item = {
'user_id': user_id,
'nickname': profile.get('user_name'),
'gender': '' if profile.get('gender') == "F" else '',
'avatar': profile.get('headurl'),
'desc': profile.get('user_text'),
'ip_location': "",
'follows': ownerCount.get("follow"),
'fans': ownerCount.get("fan"),
'interaction': ownerCount.get("photo_public"),
"last_modify_ts": utils.get_current_timestamp(),
}
utils.logger.info(f"[store.kuaishou.save_creator] creator:{local_db_item}")
await KuaishouStoreFactory.create_store().store_creator(local_db_item)

View File

@ -205,3 +205,14 @@ class KuaishouJsonStoreImplement(AbstractStore):
"""
await self.save_data_to_json(comment_item, "comments")
async def store_creator(self, creator: Dict):
"""
Kuaishou content JSON storage implementation
Args:
creator: creator dict
Returns:
"""
await self.save_data_to_json(creator, "creator")