len=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell").length

for (var i=0;i<len;i++){

console.log(document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].innerText.replace(/(\s*$)/g,""));

console.log(document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].getAttribute("data-link"))}

#说有订阅全部适用 正序

len=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell").length

console.log(len)

for (var i=0;i<len;i++){

date=document.getElementsByClassName("js_article_create_time album__item-info-item")[i].innerText.replace(/(\s*$)/g,"");

content=document.getElementsByClassName("album__item-title ellipsis_relate_title ")[i].innerText.replace(/(\s*$)/g,"");

link=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].getAttribute("data-link");

console.log(date+" "+content+" "+link)

}

#说有订阅全部适用 倒序

len=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell").length

for (var i=len-1;i>0;i--){

date=document.getElementsByClassName("js_article_create_time album__item-info-item")[i].innerText.replace(/(\s*$)/g,"");

content=document.getElementsByClassName("album__item-title ellipsis_relate_title ")[i].innerText.replace(/(\s*$)/g,"");

link=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].getAttribute("data-link");

console.log(date+" "+content+" "+link)

}

#content 格式不统一时候，date不独立取

len=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell").length

console.log(len)

for (var i=0;i<len;i++){

content=document.getElementsByClassName("album__item-content")[i].innerText.replace(/(\s*$)/g,"").replace(/[\r\n]/g," ").trim();

link=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].getAttribute("data-link");

console.log(content+" "+link)

}

#content 格式不统一时候，date不独立取;

len=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell").length

console.log(len)

for (var i=0;i<len;i++){

content=document.getElementsByClassName("album__item-content")[i].innerText.replace(/(\s*$)/g,"").replace(/[\r\n]/g," ").trim();

link=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].getAttribute("data-link");

console.log(content+" "+link)

}

dd=document.getElementsByClassName("rich_media_content js_underline_content autoTypeSetting24psection fix_apple_default_style")[0];

lens=document.getElementsByClassName("rich_media_content js_underline_content autoTypeSetting24psection fix_apple_default_style")[0].getElementsByTagName("a").length

for (var i=0;i<lens;i++) {

if (dd.getElementsByTagName("a")[i].getAttribute("textvalue")==null)

{ console.log(i+1+dd.getElementsByTagName("a")[i].innerText+" "+dd.getElementsByTagName("a")[i].getAttribute("href"));}

else

      { console.log( i+1+dd.getElementsByTagName("a")[i].getAttribute("textvalue")+" "+dd.getElementsByTagName("a")[i].getAttribute("href"));}

}

python 数据处理，写入表格

import csv

import os

filepath="/ap4/output_file.csv"

if (os.path.exists(filepath)) :

#存在，则删除文件

    os.remove(filepath)

# 打开中文文件并按行读取

all=[];

go=[];

with open('huahua.txt','r',encoding='utf-8')as f:

lines = f.readlines()

for linein lines:

s=line.split(" ")

print(str(lines.index(line))+"***"+str(len(s)))#dug 看每行的长度

    # print(s[3])  #dubug 答应每行的link

    # formatted_row = f'=HYPERLINK("{s[-1]}", "{s[1]}")'  #debug s[-1] 最后的连接

    # all.append([s[-2],s[1],formatted_row])  #倒数第一link，第二，text，第三 序号，第四日期

    # 每个人的习惯

    formatted_row =f'=HYPERLINK("{s[-1]}", "{s[0]}")'  #debug s[-1] 最后的连接

    all.append([s[-2],s[0],formatted_row])#倒数第一link，第二，text，第三 日期

# for line in all:

#    print(line)

# 打开一个 CSV 文件用于写入

with open('dateoutput_file.csv','w',newline='',encoding='utf-8-sig')as csvfile:

writer = csv.writer(csvfile)

writer.writerow(['Date','名字','key','link'])

# 遍历每一行并写入 CSV 文件的单元格

    for linein all:

writer.writerow(line)# 将每一行作为一行写入CSV

# for line in go:

    #    writer.writerow([' ',line.strip()])  # 将每一行作为一行写入CSV

print("写入完成")