pd.read_html 获取网页上的表格数据

pandas.read_html(io, match='.+', flavor=None, header=None, index_col=None, skiprows=None, 
attrs=None, parse_dates=False, thousands=',', encoding=None, decimal='.', converters=None, 
na_values=None, keep_default_na=True, displayed_only=True)

# 导入库
import pandas as pd 
import csv

# 传入要抓取的url
url1 = "http://www.compassedu.hk/qs"

#0表示选中网页中的第一个Table，或者这么使用pd.read_html(url, header=0, index_col=0,encoding = "gbk")
df1 = pd.read_html(url1)[0]
# 打印预览
df1
# 导出到CSV
df1.to_csv(r"C:UsersQDMDesktop世界大学综合排名.csv",index=0,encoding = "gbk")

# 或导出到Excel
df1.to_excel(r"C:UsersQDMDesktop世界大学综合排名.xlsx",index=0)

import pandas as pd
import csv
df2 = pd.DataFrame()
for i in range(6):
    url2 = "http://vip.stock.finance.sina.com.cn/q/go.php/vComStockHold/kind/jjzc/index.phtml?p={page}".format(page=i+1)
    df2 = pd.concat([df2,pd.read_html(url2)[0]])
    print("第{page}页抓取完成".format(page = i + 1))
    
# 保存到CSV
df2.to_csv(r"C:UsersQDMDesktop新浪财经数据.csv",encoding = "gbk",index=0)

# 保存到Excel
df2.to_excel(r"C:UsersQDMDesktop新浪财经数据.xlsx",index=0)

#  导入所需要用到的库
import pandas as pd
from pandas import DataFrame
import csv
import time

#程序计时
start = time.time() 
    
#添加列名
#"公司名称","披露类型","上市板块","保荐机构","披露时间","公告"
df3 = DataFrame(data=None,columns=["公司名称","披露类型","上市板块","保荐机构","披露时间","公告"]) 
for i in range(1,51):  
    url3 = "http://eid.csrc.gov.cn/ipo/1017/index.html"
     #必须加utf-8，否则乱码
    df3_1 = pd.read_html(url3,encoding = "utf-8")[0]
     #过滤掉最后一行和最后一列（NaN列）
    #df3_2 = df3_1.iloc[1:len(df3_1)-1,0:-1]
     #新的df添加列名
    df3_1.columns=["公司名称","披露类型","上市板块","保荐机构","披露时间","公告"]
     #数据合并
    df3 = pd.concat([df3,df3_1])
    print("第{page}页抓取完成".format(page = i))