qnloft
/
MediaCrawler
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

feat: 支持评论模式是否开启爬取选项

This commit is contained in:
Relakkes 2024-03-16 11:52:42 +08:00
parent 2d12ecb930
commit 59cd9f67a0
7 changed files with 33 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -60,6 +60,7 @@
### 运行爬虫程序
```shell
# 默认没有开启评论爬取模式，有需要请到配置文件中指定
# 从配置文件中读取关键词搜索相关的帖子并爬去帖子信息与评论
python main.py --platform xhs --lt qrcode --type search

14
config/base_config.py
View File

@ -3,7 +3,7 @@ PLATFORM = "xhs"
KEYWORDS = "python,golang"
LOGIN_TYPE = "qrcode" # qrcode or phone or cookie
COOKIES = ""
SORT_TYPE="popularity_descending" # 具体值参见media_platform.xxx.field下的枚举值，展示只支持小红书
SORT_TYPE = "popularity_descending" # 具体值参见media_platform.xxx.field下的枚举值，展示只支持小红书
CRAWLER_TYPE = "search"
# 是否开启 IP 代理
@ -19,7 +19,7 @@ HEADLESS = True
SAVE_LOGIN_STATE = True
# 数据保存类型选项配置,支持三种类型：csv、db、json
SAVE_DATA_OPTION = "json" # csv or db or json
SAVE_DATA_OPTION = "json" # csv or db or json
# 用户浏览器缓存的浏览器文件配置
USER_DATA_DIR = "%s_user_data_dir" # %s will be replaced by platform name
@ -30,12 +30,8 @@ CRAWLER_MAX_NOTES_COUNT = 20
# 并发爬虫数量控制
MAX_CONCURRENCY_NUM = 4
# 评论关键词筛选(只会留下包含关键词的评论,为空不限制)
COMMENT_KEYWORDS = [
# "真棒"
# ........................
]
# 是否开启爬评论模式, 默认不开启爬评论
ENABLE_GET_COMMENTS = False
# 指定小红书需要爬虫的笔记ID列表
XHS_SPECIFIED_ID_LIST = [
@ -78,4 +74,4 @@ XHS_CREATOR_ID_LIST = [
"61b87386000000001000b18b",
"5e8558100000000001005bc5",
# ........................
]
]

4
media_platform/bilibili/core.py
View File

@ -127,6 +127,10 @@ class BilibiliCrawler(AbstractCrawler):
:param video_id_list:
:return:
"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[BilibiliCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
return
utils.logger.info(f"[BilibiliCrawler.batch_get_video_comments] video ids:{video_id_list}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list: List[Task] = []

6
media_platform/douyin/core.py
View File

@ -132,6 +132,10 @@ class DouYinCrawler(AbstractCrawler):
return None
async def batch_get_note_comments(self, aweme_list: List[str]) -> None:
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[DouYinCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
return
task_list: List[Task] = []
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
for aweme_id in aweme_list:
@ -145,7 +149,7 @@ class DouYinCrawler(AbstractCrawler):
async with semaphore:
try:
# 将关键词列表传递给 get_aweme_all_comments 方法
comments = await self.dy_client.get_aweme_all_comments(
await self.dy_client.get_aweme_all_comments(
aweme_id=aweme_id,
crawl_interval=random.random(),
callback=douyin_store.batch_update_dy_aweme_comments

4
media_platform/kuaishou/core.py
View File

@ -144,6 +144,10 @@ class KuaishouCrawler(AbstractCrawler):
:param video_id_list:
:return:
"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[KuaishouCrawler.batch_get_note_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] = []

4
media_platform/weibo/core.py
View File

@ -166,6 +166,10 @@ class WeiboCrawler(AbstractCrawler):
:param note_id_list:
:return:
"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[WeiboCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
return
utils.logger.info(f"[WeiboCrawler.batch_get_notes_comments] note ids:{note_id_list}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list: List[Task] = []

14
media_platform/xhs/core.py
View File

@ -105,7 +105,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
notes_res = await self.xhs_client.get_note_by_keyword(
keyword=keyword,
page=page,
sort=SearchSortType(config.SORT_TYPE) if config.SORT_TYPE!='' else SearchSortType.GENERAL,
sort=SearchSortType(config.SORT_TYPE) if config.SORT_TYPE != '' else SearchSortType.GENERAL,
)
utils.logger.info(f"[XiaoHongShuCrawler.search] Search notes res:{notes_res}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
@ -122,7 +122,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
page += 1
utils.logger.info(f"[XiaoHongShuCrawler.search] Note details: {note_details}")
await self.batch_get_note_comments(note_id_list)
async def get_creators_and_notes(self) -> None:
"""Get creator's notes and retrieve their comment information."""
utils.logger.info("[XiaoHongShuCrawler.get_creators_and_notes] Begin get xiaohongshu creators")
@ -151,7 +151,8 @@ class XiaoHongShuCrawler(AbstractCrawler):
# save creator info
await xhs_store.save_creator(creator, creator_and_notes_info.get('creator'))
utils.logger.info(f"[XiaoHongShuCrawler.get_creators_and_notes] save creator info:{creator_and_notes_info.get('creator')}")
utils.logger.info(
f"[XiaoHongShuCrawler.get_creators_and_notes] save creator info:{creator_and_notes_info.get('creator')}")
else:
# get notes
notes = await self.xhs_client.get_notes_by_creator(creator, cursor)
@ -164,7 +165,8 @@ class XiaoHongShuCrawler(AbstractCrawler):
cursor = notes.get('cursor')
has_more_notes = notes.get('has_more_notes')
notes_res = notes.get('notes')
utils.logger.info(f"[XiaoHongShuCrawler.get_creators_and_notes] get creator's notes res:{notes_res}")
utils.logger.info(
f"[XiaoHongShuCrawler.get_creators_and_notes] get creator's notes res:{notes_res}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
@ -211,6 +213,10 @@ class XiaoHongShuCrawler(AbstractCrawler):
async def batch_get_note_comments(self, note_list: List[str]):
"""Batch get note comments"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[XiaoHongShuCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
return
utils.logger.info(
f"[XiaoHongShuCrawler.batch_get_note_comments] Begin batch get note comments, note list: {note_list}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)