#读入表
import pandas as pd
urls = pd.read_csv("/home/kong/Desktop/url.csv")
#print(urls.shape) #输出表的大小
nrow = urls.shape[0] #输出行数 同理,列数——shape[1]
print(nrow)
print(urls.values[0][0]) #输出指定某行某列的值
1330
https://gkcx.eol.cn/schoolhtm/schoolTemple/school420.htm
#对数据进行处理
import re
item=[]
pat = '[0-9]{1,4}'
for i in range(0,nrow):
str = urls.values[i][0]
result = re.compile(pat).findall(str)
item.append(result)
#处理结果item进行保存
import pandas as pd
#item = numpy.array(item).reshape(-1,6)
df = pd.DataFrame(item)
df.to_csv('/home/kong/Desktop/result.csv', sep=',', mode='a',index = False,header = False)