由于我用Beatifulsoup抓取的是整段整段的文本内容,请问怎么把这些抓取整段整段的内容写入CSV?
以下是代码:
# -*- coding:utf-8 -*-
import re
from urllib2 import urlopen
from bs4 import BeautifulSoup
import sys
reload(sys)
sys.setdefaultencoding( "utf-8" )
onehtml = urlopen("/article/List_2.html").read()
oneres = r'
try:
onesoup = onejiexi.findAll(id="content")[0]
con.append(onesoup.text)
res = '
'
content = re.findall(res,html,re.S)
new_content = sorted(set(content),key=content.index)
for item in new_content:
itemhtml = urlopen("/article/07/" + item)
jiexi = BeautifulSoup(itemhtml,'lxml')
soup = jiexi.findAll(id="content")[0]
con.append(soup.text)
except IndexError:
continue
f = open(r'f:/T.txt', 'w')
for t in range(len(con)):
zhujia = con[t] + "\n"
f.write(zhujia)
f.close()