pandas爬取表格

• 系列文章目录
• 下载写入excel

import pandas as pd
url="http://qhggzyjy.gov.cn/haib/jyxx/001002/001002002/20220512/f828d85d-f0b0-42f5-b77f-e4d915d313c0.html"
tables = pd.read_html(url)
print("table数量:",len(tables))

#读取第一个表

tables[0]

import pandas as pd
url="http://www.stats.gov.cn/tjsj/tjgb/jjpcgb/qgjpgb/201407/t20140731_590163.html"
tables = pd.read_html(url)
print("table数量:",len(tables))


writer = pd.ExcelWriter(r"网页表.xlsx",engine = "xlsxwriter")
i=1
for table in tables[1:]:
    df=table.fillna('类型')#替换
    if len(df)<=2:
        continue
    name=df.iloc[0, 0].replace('u3000','')#表sheet名
    df.columns = list(df.iloc[1])#选择第二行作为表
    df = df.drop([0,1], axis=0)#删除第一行
    #写入
    print(name)
    df.to_excel(writer,sheet_name = name,index=False)
    i+=1
writer.save()
writer.close()