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
|
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
# Copyright: (2013-2017) Michael Till Beck <Debianguru@gmx.de>
# License: GPL-2.0+
import urllib.request
import urllib.error
import urllib.parse
import subprocess
from lxml import etree
from cssselect import GenericTranslator
import re
# Attributes in HTML files storing URI values. These values are automatically translated to absolute URIs.
uriAttributes = [['//img[@src]', 'src'], ['//a[@href]', 'href']]
maxTitleLength = 150
class Parser:
# input: [Content], output: [Content]
def performAction(self, contentList):
pass
class Receiver(Parser):
def __init__(self, uri):
self.uri = uri
class Content:
def __init__(self, uri, encoding, title, content, contenttype):
self.uri = uri
self.encoding = encoding
self.title = title
self.content = content
self.contenttype = contenttype
# returns a short subject line
def getSubject(textContent):
global maxTitleLength
if textContent is None or len(textContent.strip()) == 0:
return 'Website has been updated'
textContent = re.sub(' +', ' ', re.sub('\s', ' ', textContent)).strip()
return (textContent[:maxTitleLength] + ' [..]') if len(textContent) > maxTitleLength else textContent
# translates all relative URIs found in trees to absolute URIs
def toAbsoluteURIs(trees, baseuri):
global uriAttributes
for tree in trees:
if isinstance(tree, str):
continue
for uriAttribute in uriAttributes:
tags = tree.xpath(uriAttribute[0])
for tag in tags:
if tag.attrib.get(uriAttribute[1]) is not None:
if urllib.parse.urlparse(tag.attrib[uriAttribute[1]]).scheme == '':
tag.attrib[uriAttribute[1]] = urllib.parse.urljoin(baseuri, tag.attrib[uriAttribute[1]])
class URLReceiver(Receiver):
def __init__(self, uri, contenttype='html', encoding='utf-8', userAgent=None, accept=None):
super().__init__(uri)
self.contenttype = contenttype
self.encoding = encoding
self.userAgent = userAgent
self.accept = accept
# input: [Content], output: [Content]
def performAction(self, contentList=None):
if contentList is None:
contentList = []
# open website
req = urllib.request.Request(self.uri)
if self.userAgent is not None:
req.add_header('User-Agent', self.userAgent)
if self.accept is not None:
req.add_header('Accept', self.accept)
with urllib.request.urlopen(req) as thefile:
filecontent = thefile.read().decode(self.encoding, errors='ignore')
contentList.append(Content(uri=self.uri, encoding=self.encoding, title=None, content=filecontent, contenttype=self.contenttype))
return contentList
class CommandReceiver(Receiver):
def __init__(self, command, contenttype='text', encoding='utf-8'):
super().__init__(command)
self.encoding = encoding
self.command = command
self.contenttype = contenttype
# input: [Content], output: [Content]
def performAction(self, contentList=None):
if contentList is None:
contentList = []
# run command and retrieve output
process = subprocess.Popen(self.command, stdout=subprocess.PIPE, shell=True, close_fds=True)
thefile = process.stdout
result = thefile.read().decode(self.encoding, errors='ignore')
thefile.close()
if process.wait() != 0:
raise Exception("process terminated with an error")
contentList.append(Content(uri=None, encoding=self.encoding, title=None, content=result, contenttype=self.contenttype))
return contentList
class XPathParser(Parser):
def __init__(self, contentxpath, titlexpath=None):
self.contentxpath = contentxpath
self.titlexpath = titlexpath
# input: [Content], output: [Content]
def performAction(self, contentList):
result = []
for content in contentList:
result.extend(self.parseOneObject(content))
return result
# input: Content, output: [Content]
def parseOneObject(self, content):
baseuri = content.uri
if content.contenttype == 'html':
parser = etree.HTMLParser(encoding=content.encoding)
else:
parser = etree.XMLParser(recover=True, encoding=content.encoding)
tree = etree.fromstring(content.content, parser=parser)
# xpath
contentresult = [] if self.contentxpath is None else tree.xpath(self.contentxpath)
titleresult = [] if self.titlexpath is None else tree.xpath(self.titlexpath)
# translate relative URIs to absolute URIs
if content.contenttype == 'html':
basetaglist = tree.xpath('/html/head/base')
if len(basetaglist) != 0:
baseuri = basetaglist[0].attrib['href']
if len(contentresult) != 0:
toAbsoluteURIs(contentresult, baseuri)
if len(titleresult) != 0:
toAbsoluteURIs(titleresult, baseuri)
if self.contentxpath and len(contentresult) == 0:
raise Exception('WARNING: content selector became invalid!')
if self.titlexpath and len(titleresult) == 0:
raise Exception('WARNING: title selector became invalid!')
contents = []
titles = []
if isinstance(contentresult, str):
contents = [contentresult]
else:
if len(contentresult) == 0:
contentresult = titleresult
contents = [etree.tostring(s, encoding=content.encoding, pretty_print=True).decode(content.encoding, errors='ignore') for s in contentresult]
if isinstance(titleresult, str):
titles = [getSubject(titleresult)]*len(contents)
else:
if len(titleresult) == 0 or len(titleresult) != len(contentresult):
titleresult = contentresult
titles = [getSubject(etree.tostring(s, method='text', encoding=content.encoding).decode(content.encoding, errors='ignore')) for s in titleresult]
result = []
for i in range(0, len(contents)):
result.append(Content(uri=content.uri, encoding=content.encoding, title=titles[i], content=contents[i], contenttype=content.contenttype))
return result
class CSSParser(Parser):
def __init__(self, contentcss, titlecss=None):
contentxpath = GenericTranslator().css_to_xpath(contentcss)
titlexpath = None
if titlecss is not None:
titlexpath = GenericTranslator().css_to_xpath(titlecss)
self.xpathparser = XPathParser(contentxpath=contentxpath, titlexpath=titlexpath)
# input: [Content], output: [Content]
def performAction(self, contentList):
return self.xpathparser.performAction(contentList)
class RegExParser(Parser):
def __init__(self, contentregex, titleregex=None):
self.contentregex = contentregex
self.titleregex = titleregex
# input: [Content], output: [Content]
def performAction(self, contentList):
result = []
for content in contentList:
result.extend(self.parseOneObject(content))
return result
# input: Content, output: [Content]
def parseOneObject(self, content):
contents = []
titles = []
if self.contentregex is not None:
for c in re.findall(r'' + self.contentregex, content.content, re.M):
if len(c.strip()) != 0:
contents.append(c)
if self.titleregex is not None:
for c in re.findall(r'' + self.titleregex, content.title, re.M):
if len(c.strip()) != 0:
titles.append(c)
if self.contentregex is not None and len(contents) == 0:
raise Exception('WARNING: content regex became invalid!')
elif self.titleregex is not None and len(titles) == 0:
raise Exception('WARNING: title regex became invalid!')
else:
if len(contents) == 0:
contents = titles
if len(titles) == 0 or len(titles) != len(contents):
titles = [getSubject(c) for c in contents]
result = []
for i in range(0, len(contents)):
result.append(Content(uri=content.uri, encoding=content.encoding, title=titles[i], content=contents[i], contenttype=content.contenttype))
return result
|
