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*$)/g,""));
console.log(document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].getAttribute("data-link"))}
#說有訂閱全部適用 正序
len=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell").length
console.log(len)
for (var i=0;i<len;i++){
date=document.getElementsByClassName("js_article_create_time album__item-info-item")[i].innerText.replace(/(\s*$)/g,"");
content=document.getElementsByClassName("album__item-title ellipsis_relate_title ")[i].innerText.replace(/(\s*$)/g,"");
link=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].getAttribute("data-link");
console.log(date+" "+content+" "+link)
}
#說有訂閱全部適用 倒序
len=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell").length
for (var i=len-1;i>0;i--){
date=document.getElementsByClassName("js_article_create_time album__item-info-item")[i].innerText.replace(/(\s*$)/g,"");
content=document.getElementsByClassName("album__item-title ellipsis_relate_title ")[i].innerText.replace(/(\s*$)/g,"");
link=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell")[i].getAttribute("data-link");
console.log(date+" "+content+" "+link)
}
#content 格式不統(tǒng)一時候瑟啃，date不獨立取
len=document.getElementsByClassName("album__list-item js_album_item js_wx_tap_highlight wx_tap_cell").length
console.log(len)
for (var i=0;i<len;i++){
content=document.getElementsByClassName("album__item-content")[i].innerText.replace(/(\s*$)/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 格式不統(tǒng)一時候舔亭，date不獨立取;
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 數(shù)據(jù)處理洒忧，寫入表格
import csv
import os
filepath="/ap4/output_file.csv"
if (os.path.exists(filepath)) :
#存在孵户，則刪除文件
? ? os.remove(filepath)
# 打開中文文件并按行讀取
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 看每行的長度
? ? # print(s[3])? #dubug 答應每行的link
? ? # formatted_row = f'=HYPERLINK("{s[-1]}", "{s[1]}")'? #debug s[-1] 最后的連接
? ? # all.append([s[-2],s[1],formatted_row])? #倒數(shù)第一link芦昔，第二，text，第三 序號察皇，第四日期
? ? # 每個人的習慣
? ? formatted_row =f'=HYPERLINK("{s[-1]}", "{s[0]}")'? #debug s[-1] 最后的連接
? ? all.append([s[-2],s[0],formatted_row])#倒數(shù)第一link不傅，第二旅掂，text，第三 日期
# for line in all:
#? ? print(line)
# 打開一個 CSV 文件用于寫入
with open('dateoutput_file.csv','w',newline='',encoding='utf-8-sig')as csvfile:
writer = csv.writer(csvfile)
writer.writerow(['Date','名字','key','link'])
# 遍歷每一行并寫入 CSV 文件的單元格
? ? for linein all:
writer.writerow(line)# 將每一行作為一行寫入CSV
# for line in go:
? ? #? ? writer.writerow([' ',line.strip()])? # 將每一行作為一行寫入CSV
print("寫入完成")
