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")
