增加telegram机器人推送p站图片脚本

.gitignore

@@ -73,3 +73,5 @@ fabric.properties
 
 .idea
 time.log
+
+.DS_Store

README.md

@@ -4,3 +4,5 @@
     历史记录并提交到远程仓库。
 2. [UEFI启动光盘镜像制作](grub)
 	支持UEFI启动的GRUB2 ISO光盘镜像的制作
+3. [Telegram机器人推送P站图片](pixiv)
+    爬取P站上的图片，并通过Telegram机器人推送到目标聊天室

pixiv/config.json.example

@@ -0,0 +1,8 @@
+{
+  "basePath": "本地缓存路径，包括接口数据，图片等",
+  "telegramToken": "telegram 机器人申请的API Token",
+  "chatId": "推送目标聊天的唯一标识符或目标频道的用户名",
+  "anonfilesToken": "https://anonfiles.com/ 申请的API Token",
+  "mode": "Pixiv排行榜类型，有效值：daily/weekly/monthly/rookie/daily_r18/weekly_r18/male_r18/female_r18/r18g,分别是日榜/周榜/月榜/新人榜/日榜r18/周榜r18/受男性欢迎r18/受女性欢迎r18/r18g",
+  "content": "Pixiv排行榜类型，有效值：illust/ugoira/manga/,分别是插画/动图/漫画",
+}

pixiv/pixiv.sh

@@ -0,0 +1,165 @@
+#!/bin/bash
+
+config_file=$1
+if [ -z $config_file ]
+then
+   echo 'The cache directory must be specified'
+   exit 1
+fi
+if [ ! -f $config_file ]
+then
+        echo 'config file：$config_file not found'
+        exit 1
+fi
+if [ ! -f `which jq` ]
+then
+        echo 'To run this script, you need to install jq，https://stedolan.github.io/jq/'
+        exit 1
+else
+        echo "jq version:`jq --version`"
+fi
+
+basePath=`cat $config_file|jq -r .basePath`
+if [ ! -f $basePath ]
+then
+        mkdir -p $basePath
+fi
+cd $basePath
+
+telegramToken=`cat $config_file | jq -r .telegramToken`
+baseApi="https://api.telegram.org/bot$telegramToken"
+chat_id=`cat $config_file | jq .chatId`
+mode=`cat $config_file | jq -r .mode`
+content=`cat $config_file | jq -r .content`
+rank_url="https://www.pixiv.net/ranking.php?mode=$mode&content=$content&p=1&format=json"
+today=`date "+%Y-%m-%d"`
+_today=`echo $today|sed -e 's/-/\\\\-/g'`
+rank_json=$today.json
+commands_file=$today.sh
+anonfiles_token=`cat $config_file | jq .anonfilesToken`
+touch $commands_file && chmod +x $commands_file
+sleep 30
+curl -v -d chat_id=$chat_id -d parse_mode=HTML  -d text="Pixiv排行榜已更新，30秒后开始处理<a href='https://www.pixiv.net/ranking.php?mode%3D$mode%26content%3D$content'>$today日榜</a>数据。%0A%0A<strong>排名是什么？</strong>%0A排名是以pixiv上所有公开作品为对象的统计以及排名。%0A毎日0:00～23时59分59秒的阅览树・「赞！」数等为排名的依据，期结果由pixiv独自的算法「pixiv rank β」决定。统计结果于每日中午12:00公开。%0A<a href='https://www.pixiv.help/hc/zh-cn/categories/360001065093-%E6%9C%89%E5%85%B3%E6%8E%92%E8%A1%8C%E6%A6%9C'>有关排行榜</a>" $baseApi/sendMessage
+
+if [ ! -f $rank_json ]
+then
+        echo "get data from $rank_url"
+        curl -v $rank_url >$rank_json
+fi
+length=`jq '.contents|length' $rank_json`
+fileCountSize=0
+maxSize=2500
+fileList=''
+media=''
+fileCount=0
+maxFileCount=10
+tarFile=$today.tar.gz
+originalFileList=''
+for index in `seq 1 $length`
+do
+        index=$((index-1))
+        pid=`jq  --argjson index $index '.contents[$index].illust_id' $rank_json`
+        artworkLink="https://www.pixiv.net/artworks/$pid"
+        rank=`jq  --argjson index $index '.contents[$index].rank' $rank_json`
+        yes_rank=`jq  --argjson index $index '.contents[$index].yes_rank' $rank_json`
+        if [ $yes_rank -eq 0 ]
+        then
+          rank_info="#首次登场"
+        else
+          rank_info="\#rank$rank 之前 \#rank$yes_rank"   
+        fi
+        echo "pid=$pid,artworkLink=$artworkLink,rank_info=$rank_info"
+        png_html_file=$pid.html
+        if [ ! -f $png_html_file ]
+        then
+                sleep 1
+                echo "get data from $artworkLink"
+                curl -v $artworkLink >$png_html_file
+        fi
+        json_file=$pid.json
+        if [ ! -f $json_file ]
+        then
+                egrep -o "content='{\"timestamp.*].{3}" $png_html_file | sed -e "s/content='//" >$json_file
+        fi
+        pageCount=`jq --arg pid $pid '.illust[$pid].pageCount' $json_file`
+        original_url=`jq --arg pid $pid '.illust[$pid].urls.original' $json_file | sed -e 's/\"//g'`
+        small_url=`jq --arg pid $pid '.illust[$pid].urls.small' $json_file | sed -e 's/\"//g'`
+        title=`jq -r --arg pid $pid '.illust[$pid].title' $json_file`
+        description=`jq -r --arg pid $pid '.illust[$pid].description' $json_file`
+        userName=`jq -r --arg pid $pid '.illust[$pid].userName' $json_file`
+        userId=`jq -r --arg pid $pid '.illust[$pid].userId' $json_file`
+        likeCount=`jq --arg pid $pid '.illust[$pid].likeCount' $json_file`
+        bookmarkCount=`jq --arg pid $pid '.illust[$pid].bookmarkCount' $json_file`
+        viewCount=`jq --arg pid $pid '.illust[$pid].viewCount' $json_file`
+        tag=`jq -r  --arg pid $pid '.illust[$pid].tags.tags[].tag' $json_file|sed -e 's/^/\\#/g'|sed ':a;N;s/\n/ /;t a;'`
+        
+        echo -e "pageCount=$pageCount,original_url=$original_url,small_url=$small_url\n\
+        title=$title,description=$description,userName=$userName\n\
+        likeCount=$likeCount,bookmarkCount=$bookmarkCount,viewCount=$viewCount\n\
+        tag=$tag"
+        for page in `seq 1 $pageCount`
+        do
+                page=$((page - 1))
+                page_original_url=`echo $original_url | sed -e "s/p0/p$page/"`
+                page_small_url=`echo $small_url | sed -e"s/p0/p$page/"`
+                original_file_name=`echo $page_original_url | egrep -o "$pid.*"`
+                small_file_name=`echo $page_small_url | egrep -o "$pid.*"`
+                echo "download image file name=$original_file_name,url=$page_original_url"
+                if [ ! -f $original_file_name ]
+                then
+                        curl -v -H 'referer: https://www.pixiv.net/' $page_original_url -o $original_file_name
+                fi
+                originalFileList="$originalFileList $original_file_name"
+                echo "download image file name=$small_file_name,url=$page_small_url"
+                if [ ! -f $small_file_name ]
+                then
+                        curl -v -H 'referer: https://www.pixiv.net/' $page_small_url -o $small_file_name
+                fi
+                if [ $page -eq 0 ]
+                then
+                        media="$media,{\"type\":\"photo\",\"media\":\"attach://$small_file_name\",\"parse_mode\":\"HTML\",\"caption\":\"$rank_info\n<a href=\\\"$artworkLink\\\">$title</a>\n<a href=\\\"https://www.pixiv.net/users/$userId\\\">$userName</a>\n$tag\"}"
+                        fileList=$fileList' -F '$small_file_name'=@'$basePath'/'$small_file_name
+                        fileCount=$((fileCount + 1))
+                        fileSize=`du $small_file_name | awk '{print $1}'`
+                        fileCountSize=$((fileCountSize + fileSize))
+                        echo "fileCountSize=$fileCountSize,fileCount=$fileCount"
+                fi
+                if [[ $fileCountSize -gt $maxSize || $fileCount -eq $maxFileCount ]]
+                then
+                        echo "sleep 1m" >>$commands_file
+                        echo "curl -v -F  chat_id=$chat_id $fileList -F media='[`echo $media | cut -c 2-`]' $baseApi/sendMediaGroup" >>$commands_file
+                        echo >>$commands_file
+                        echo >>$commands_file
+                        echo >>$commands_file
+                        fileCountSize=0
+                        fileList=''
+                        media=''
+                        fileCount=0
+                fi
+        done
+done
+if [ $fileCount -gt 0 ]
+then
+        echo "curl -v -F  chat_id=$chat_id $fileList -F media='[`echo $media | cut -c 2-`]' $baseApi/sendMediaGroup" >>$commands_file
+fi
+sed -i '1d' $commands_file
+hasSend=$today.hasSend
+if [ ! -f $hasSend ]
+then
+        bash -c ./$commands_file
+        touch $hasSend
+fi
+
+if [ ! -f $tarFile ]
+then
+        tar -zcvf $tarFile $originalFileList
+fi
+uploadResFile=$today.upload
+if [ ! -f $uploadResFile ]
+then
+        curl -v -F "file=@$tarFile" -F token=$anonfiles_token https://api.anonfiles.com/upload -o $uploadResFile     
+fi
+shortUrl=`cat $uploadResFile | jq -r .data.file.url.short`
+readable=`cat $uploadResFile | jq -r .data.file.metadata.size.readable|sed -e 's/\./\\\\./'`
+echo "shortUrl=$shortUrl,readable=$readable"
+curl -v -d text="$_today日榜原图（$readable）已打包上传到服务器，[下载地址]($shortUrl) \#图包下载 \#资源下载 \#下载" -d chat_id=$chat_id -d parse_mode=MarkdownV2 $baseApi/sendMessage