我在Python 2.7.13上编写了这段代码,用于从网站上抓取数据表。
import urllib2
from bs4 import BeautifulSoup
import csv
import os
out=open("proba.csv","rb")
data=csv.reader(out)
def make_soup(url):
thepage = urllib2.urlopen(url)
soupdata = BeautifulSoup(thepage, "html.parser")
return soupdata
maindatatable=""
soup = make_soup("https://www.mnb.hu/arfolyamok")
for record in soup.findAll('tr'):
datatable=""
for data in record.findAll('td'):
datatable=datatable+","+data.text
maindatatable = maindatatable + "\n" + datatable[1:]
header = "Penznem,Devizanev,Egyseg,Penznemforintban"
print maindatatable
file = open(os.path.expanduser("proba.csv"),"wb")
utf16_str1 =header.encode('utf16')
utf16_str2 = maindatatable.encode('utf16')
file.write(utf16_str1)
file.write(utf16_str2)
file.close()
我想将其导出为CSV,接下来的4行:
“Penznem Devaizanev Egyseg Penznemforintban”
数据用“,”分隔,但最后两个值是一行。 (283,45)
我该如何解决?
答案 0 :(得分:0)
你不能直接避免最后一次昏迷,但
你可以做的就是使用另一个seprator,即;(分号) 当你在exel中打开文件时,将select(;)分号作为seprator进行计算,你会得到预期的结果!
import urllib2
from bs4 import BeautifulSoup
import csv
import os
out=open("proba.csv","rb")
data=csv.reader(out)
def make_soup(url):
thepage = urllib2.urlopen(url)
soupdata = BeautifulSoup(thepage, "html.parser")
return soupdata
maindatatable=""
soup = make_soup("https://www.mnb.hu/arfolyamok")
for record in soup.findAll('tr'):
datatable=""
for data in record.findAll('td'):
datatable=datatable+";"+data.text
maindatatable = maindatatable + "\n" + datatable[1:]
header = "Penznem;Devizanev;Egyseg;Penznemforintban"
print maindatatable
file = open(os.path.expanduser("proba.csv"),"wb")
utf16_str1 =header.encode('utf16')
utf16_str2 = maindatatable.encode('utf16')
file.write(utf16_str1)
file.write(utf16_str2)
file.close()