1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
| #encoding=utf-8
import jieba
from bs4 import BeautifulSoup
import re
import requests
#虚词列表
excludeWords = ()
with open('excludeWords','r+') as f:
excludeWords=f.read()
f.close()
excludeWords = eval(excludeWords)
class domNode:
parentNode=None
currNode=None
innerText=None
posi=0
def __init__(self,parentNode,currNode,innerText,posi):
self.parentNode=parentNode
self.currNode=currNode
self.innerText=innerText
self.posi=posi
def levenshtein(a,b):
"相似度计算."
n, m = len(a), len(b)
if n > m:
# Make sure n <= m, to use O(min(n,m)) space
a,b = b,a
n,m = m,n
current = range(n+1)
for i in range(1,m+1):
previous, current = current, [i]+[0]*n
for j in range(1,n+1):
add, delete = previous[j]+1, current[j-1]+1
change = previous[j-1]
if a[j-1] != b[i-1]:
change = change + 1
current[j] = min(add, delete, change)
return current[n]
def filter_words(sourList,filterList):
dest=[]
if type(sourList)!="<type 'set'>":
dest=list(sourList)
else:
dest=sourList
if filterList==None or len(filterList)==0:
return dest
dest = [ i for i in dest if not(i in filterList) ]
return dest
def getContextByNode(htmlSoup,titleKeyWordList,filterList):
sentenceList=jieba.cut(htmlSoup.string)
sentenceList=filter_words(sentenceList,excludeWords)
sentenceList=filter_words(sentenceList,filterList)
if levenshtein(sentenceList,titleKeyWordList)>=len(sentenceList):
return None
return sentenceList
def getHTMLContext(html,filterList):
"获取html的正文内容，不包含tag标签"
if html==None:
return ""
if len(html)==0:
return ""
encodeHtml=encodeSpecialTag(html)
htmlSoup=BeautifulSoup(encodeHtml)
#去除script和style内容
if htmlSoup.script!=None:
htmlSoup.script.replaceWith("")
if htmlSoup.style!=None:
htmlSoup.style.replaceWith("")
if htmlSoup==None or htmlSoup.html==None or htmlSoup.html.head==None or htmlSoup.html.head.title==None:
return ""
#提取标题
title=htmlSoup.html.head.title.string
#print(title)
if title==None:
return ""
titleKeyWordList=jieba.cut(title)
titleKeyWordList = list(filter(lambda w:w.strip(),titleKeyWordList))
titleKeyWordList=filter_words(titleKeyWordList,excludeWords)
titleKeyWordList=filter_words(titleKeyWordList,filterList)
#print(titleKeyWordList)
# 实词是否为空
if len(titleKeyWordList)==0:
return ""
markWindowsList=getMarkWindowsList(htmlSoup.html.body)
#print(type(markWindowsList))
#print(markWindowsList)
markWindowsList = sorted(markWindowsList,key=cmp_to_key(lambda x,y: cmp(x.posi, y.posi)))
#print(titleKeyWordList)
context=""
for item in markWindowsList:
innerText=item.innerText
markWindowKeyWordList=jieba.cut(innerText)
markWindowKeyWordList=filter_words(markWindowKeyWordList,excludeWords)
markWindowKeyWordList=filter_words(markWindowKeyWordList,filterList)
kl=len(markWindowKeyWordList)
if kl==0:
continue
l=levenshtein(titleKeyWordList,markWindowKeyWordList)
#print(markWindowsList,l)
if l<kl:
context+=innerText.strip()+'.\n'
return decodeSpecialTag(context)
def cmp(x,y):
return x-y
def cmp_to_key(mycmp):
'Convert a cmp= function into a key= function'
class K(object):
def __init__(self, obj, *args):
self.obj = obj
def __lt__(self, other):
return mycmp(self.obj, other.obj) < 0
def __gt__(self, other):
return mycmp(self.obj, other.obj) > 0
def __eq__(self, other):
return mycmp(self.obj, other.obj) == 0
def __le__(self, other):
return mycmp(self.obj, other.obj) <= 0
def __ge__(self, other):
return mycmp(self.obj, other.obj) >= 0
def __ne__(self, other):
return mycmp(self.obj, other.obj) != 0
return K
def repl(m):
contents = m.group(3)
if contents == '</p>':
return '[[p]]'
return contents
def encodeSpecialTag(html):
"这里的规则有助于正文内容的识别,还可以保留部分标签，如下面就保留了P，br等标签"
comment=re.compile(r"<!--[.\s\S]*?-->")
html=comment.sub('', html)
#h tag
hPre=re.compile(r"<[\t ]*?[hH][1-6][^<>]*>")
html=hPre.sub('[[h4]]', html)
hAfter=re.compile(r"<[\t ]*?/[hH][1-6][^<>]*>")
html=hAfter.sub('[[/h4]]', html)
br=re.compile(r"<[ \t]*?br[^<>]*>", re.IGNORECASE)
html=br.sub('[[br /]]', html)
hr=re.compile(r"<[ \t]*?hr[^<>]*>", re.IGNORECASE)
html=hr.sub('[[hr /]]', html)
strongPre=re.compile(r"<[\t ]*?strong[^<>]*>", re.IGNORECASE)
html=strongPre.sub('[[strong]]', html)
strongAfter=re.compile(r"<[\t ]*?/strong[^<>]*>", re.IGNORECASE)
html=strongAfter.sub('[[/strong]]', html)
# labelPre=re.compile(r"<[\t ]*?label[^<>]*>", re.IGNORECASE)
# html=labelPre.sub('[[label]]', html)
# labelAfter=re.compile(r"<[\t ]*?/label[^<>]*>", re.IGNORECASE)
# html=labelAfter.sub('[[/label]]', html)
#
# spanPre=re.compile(r"<[\t ]*?span[^<>]*>", re.IGNORECASE)
# html=spanPre.sub('[[span]]', html)
# spanAfter=re.compile(r"<[\t ]*?/span[^<>]*>", re.IGNORECASE)
# html=spanAfter.sub('[[/span]]', html)
pPre=re.compile(r"<[\t ]*?/p[^<>]*>[^<>]*<[\t ]*?p[^<>]*>", re.IGNORECASE)
html=pPre.sub('[[/p]][[p]]', html)
pAfter=re.compile(r"<[\t ]*?p[^<>]*>(?=[^(\[\[)]*\[\[/p\]\]\[\[p\]\])", re.IGNORECASE)
html=pAfter.sub('[[p]]', html)
#
# pAfter=re.compile(r"(\[\[p\]\].*>)([^<>]*)(</p>)", re.IGNORECASE)
# html=pAfter.sub(repl,html)
aPre=re.compile(r"<[\t ]*?a[^<>]*>", re.IGNORECASE)
html=aPre.sub('', html)
aAfter=re.compile(r"<[\t ]*?/a[^<>]*>", re.IGNORECASE)
html=aAfter.sub('', html)
# chardet.detect(html)['encoding']
js=re.compile(r"<(script)[\w\s\S.\u4e00-\u9fa5\uac00-\ud7ff\u30a0-\u30ff\u3040-\u309f]*?</\1>(?s)", re.IGNORECASE)
html=js.sub('', html)
css=re.compile(r"<(style)[\w\s\S.\u4e00-\u9fa5\uac00-\ud7ff\u30a0-\u30ff\u3040-\u309f]*?</\1>(?s)", re.IGNORECASE)
html=css.sub('', html)
return html
def decodeSpecialTag(html):
html=html.replace("[[strong]]","<strong>")
html=html.replace("[[/strong]]","</strong>")
html=html.replace("[[hr /]]","<hr />")
html=html.replace("[[br /]]","<br />")
html=html.replace("[[h4]]","<h4>")
html=html.replace("[[/h4]]","</h4>")
html=html.replace("[[label]]","<label>")
html=html.replace("[[/label]]","</label>")
html=html.replace("[[span]]","<span>")
html=html.replace("[[/span]]","</span>")
html=html.replace("[[p]]","<p>")
html=html.replace("[[/p]]","</p>")
return html
def getMarkWindowsList(bodySoup):
#过滤a标签
nodeQueue=[]
innerTextNodeList=[]
nodeQueue.append(bodySoup)
i=0
while len(nodeQueue)>0:
currNode=nodeQueue[0]
del nodeQueue[0]
for childNode in currNode:
if childNode.string!=None:
innerText=childNode.string
innerText=innerText.replace('\r\n','').replace('\r','').replace('\n','')
tmp=innerText.replace('\t','').replace(' ',' ').replace(' ',' ')
tmpInt=len(tmp.replace(" ",""))
if tmpInt==0:continue
if len(tmp.split(' '))<=2 and len(innerText)-tmpInt>tmpInt:continue
if len(tmp)>1 and innerText.find("©")==-1 and innerText.find("©")==-1 :
dn=domNode(childNode.parent,childNode,innerText,i)
innerTextNodeList.append(dn)
i+=1
# print "i",
# print i,
# print "=",
# print childNode
else:
#这里的规则可能有助于垃圾信息的排除
if childNode.name!=None and childNode.name=='style':continue
if childNode.name!=None and childNode.name=='script':continue
if childNode.name!=None and childNode.name=="a" and len(childNode.text)<=2:continue
if childNode.name!=None and childNode.parent.name!=None and childNode.name=="span" and ( childNode.parent.name=="li" )and len(childNode.text)<=3:
continue
nodeQueue.append(childNode)
return innerTextNodeList
#soup=BeautifulSoup(html)
def test():
headers={
'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36'
}
c=requests.get('http://www.xfocus.net/articles/200808/984.html',headers=headers)
content=c.content.decode('gbk')
#content=c.text
# #print(content)
print(getHTMLContext(content,['']))
if __name__ == '__main__':
test()
|
