jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-05-09 12:07:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 知乎支持创作者主页数据爬取(回答、文章、视频)

Browse Source
This commit is contained in:
Relakkes
2024-10-16 21:02:27 +08:00
parent af9d2d8e84
commit da8f1c62b8
8 changed files with 511 additions and 66 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
schema/tables.sql
View File

@@ -474,6 +474,7 @@ CREATE TABLE `zhihu_content` (
`user_link` varchar(255) NOT NULL COMMENT '用户主页链接',
`user_nickname` varchar(64) NOT NULL COMMENT '用户昵称',
`user_avatar` varchar(255) NOT NULL COMMENT '用户头像地址',
`user_url_token` varchar(255) NOT NULL COMMENT '用户url_token',
`add_ts` bigint NOT NULL COMMENT '记录添加时间戳',
`last_modify_ts` bigint NOT NULL COMMENT '记录最后修改时间戳',
PRIMARY KEY (`id`),
@@ -482,6 +483,7 @@ CREATE TABLE `zhihu_content` (
) ENGINE=InnoDB DEFAULT CHARSET=utf8mb4 COLLATE=utf8mb4_0900_ai_ci COMMENT='知乎内容（回答、文章、视频）';
CREATE TABLE `zhihu_comment` (
`id` int NOT NULL AUTO_INCREMENT COMMENT '自增ID',
`comment_id` varchar(64) NOT NULL COMMENT '评论ID',
@@ -513,10 +515,17 @@ CREATE TABLE `zhihu_creator` (
`user_link` varchar(255) NOT NULL COMMENT '用户主页链接',
`user_nickname` varchar(64) NOT NULL COMMENT '用户昵称',
`user_avatar` varchar(255) NOT NULL COMMENT '用户头像地址',
`url_token` varchar(64) NOT NULL COMMENT '用户URL Token',
`gender` varchar(16) DEFAULT NULL COMMENT '用户性别',
`ip_location` varchar(64) DEFAULT NULL COMMENT 'IP地理位置',
`follows` int NOT NULL DEFAULT '0' COMMENT '关注数',
`fans` int NOT NULL DEFAULT '0' COMMENT '粉丝数',
`follows` int NOT NULL DEFAULT 0 COMMENT '关注数',
`fans` int NOT NULL DEFAULT 0 COMMENT '粉丝数',
`anwser_count` int NOT NULL DEFAULT 0 COMMENT '回答数',
`video_count` int NOT NULL DEFAULT 0 COMMENT '视频数',
`question_count` int NOT NULL DEFAULT 0 COMMENT '问题数',
`article_count` int NOT NULL DEFAULT 0 COMMENT '文章数',
`column_count` int NOT NULL DEFAULT 0 COMMENT '专栏数',
`get_voteup_count` int NOT NULL DEFAULT 0 COMMENT '获得的赞同数',
`add_ts` bigint NOT NULL COMMENT '记录添加时间戳',
`last_modify_ts` bigint NOT NULL COMMENT '记录最后修改时间戳',
PRIMARY KEY (`id`),