python 爬取网页内容

#encoding:UTF-8
import urllib
import urllib.request
import bs4
from bs4 import BeautifulSoup as bs
def test1():
url = "http://www.stylusstudio.com/edifact/D95B/CODECO.htm"
resp = urllib.request.urlopen(url)
data = resp.read().decode('UTF-8')
soup = bs(data, 'html.parser')
segment11= soup.find_all('table')
segment1=segment11[7].find_all('tr')#表示第几个table，此时表示进去html网页中的第7个table f2=open('./text1.txt','a',encoding='cp852')
for item in segment1: print(item)
'''
<tr class="FrameTreeFont"><td><span class="FrameDrawFont">│
<span class="FrameHideFont">─</span>│<span class="FrameHideFont">─</span>├─</span>
<a class="FrameItemFont" href="DAM_.htm" target="classFrame" title="Damage">DAM</a>
Damage</td><td align="right"><span class="FrameDetailFont"> ×1 
</span></td><td><span class="FrameDetailFont">(M)</span></td></tr>
''' print(item.get_text())#以文本方式呈现
'''
│─│─├─DAM Damage ×1 (M)
'''
# print(item.td.span.get_text())#获取具体标签内部内容
print([text for text in item.stripped_strings] )#以列表方式呈现
'''
['│', '─', '│', '─', '├─', 'DAM', 'Damage', '×1', '(M)']
'''
'''
soup.get_text("|")#u'\nI linked to |example.com|\n'进一步，通过strip去除掉文本每个位的头尾空白。 soup.get_text("|", strip=True)#u'I linked to|example.com'
'''
f2.writelines(str([text for text in item.stripped_strings])+'\n')
f2.close()
if __name__=='__main__':
test1()