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
|
>>> import mechanize
>>> from mechanize._response import test_html_response
>>> from mechanize._html import LinksFactory, FormsFactory, TitleFactory, \
... MechanizeBs, \
... RobustLinksFactory, RobustFormsFactory, RobustTitleFactory
mechanize.ParseError should be raised on parsing erroneous HTML.
For backwards compatibility, mechanize.ParseError derives from
exception classes that mechanize used to raise, prior to version
0.1.6.
>>> import sgmllib
>>> import HTMLParser
>>> issubclass(mechanize.ParseError, sgmllib.SGMLParseError)
True
>>> issubclass(mechanize.ParseError, HTMLParser.HTMLParseError)
True
>>> def create_response(error=True):
... extra = ""
... if error:
... extra = "<!!!>"
... html = """\
... <html>
... <head>
... <title>Title</title>
... %s
... </head>
... <body>
... <p>Hello world
... </body>
... </html>
... """ % extra
... return test_html_response(html)
>>> f = LinksFactory()
>>> f.set_response(create_response(), "http://example.com", "latin-1")
>>> list(f.links()) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
ParseError:
>>> f = FormsFactory()
>>> f.set_response(create_response(), "latin-1")
>>> list(f.forms()) # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
ParseError:
>>> f = TitleFactory()
>>> f.set_response(create_response(), "latin-1")
>>> f.title() # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
ParseError:
Accessing attributes on Factory may also raise ParseError
>>> def factory_getattr(attr_name):
... fact = mechanize.DefaultFactory()
... fact.set_response(create_response())
... getattr(fact, attr_name)
>>> factory_getattr("title") # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
ParseError:
>>> factory_getattr("global_form") # doctest: +IGNORE_EXCEPTION_DETAIL
Traceback (most recent call last):
ParseError:
BeautifulSoup ParseErrors:
XXX If I could come up with examples that break links and forms
parsing, I'd uncomment these!
>>> def create_soup(html):
... r = test_html_response(html)
... return MechanizeBs("latin-1", r.read())
#>>> f = RobustLinksFactory()
#>>> html = """\
#... <a href="a">
#... <frame src="b">
#... <a href="c">
#... <iframe src="d">
#... </a>
#... </area>
#... </frame>
#... """
#>>> f.set_soup(create_soup(html), "http://example.com", "latin-1")
#>>> list(f.links()) # doctest: +IGNORE_EXCEPTION_DETAIL
#Traceback (most recent call last):
#ParseError:
#>>> html = """\
#... <table>
#... <tr><td>
#... <input name='broken'>
#... </td>
#... </form>
#... </tr>
#... </form>
#... """
#>>> f = RobustFormsFactory()
#>>> f.set_response(create_response(), "latin-1")
#>>> list(f.forms()) # doctest: +IGNORE_EXCEPTION_DETAIL
#Traceback (most recent call last):
#ParseError:
#>>> f = RobustTitleFactory()
#>>> f.set_soup(create_soup(""), "latin-1")
#>>> f.title() # doctest: +IGNORE_EXCEPTION_DETAIL
#Traceback (most recent call last):
#ParseError:
Utility class for caching forms etc.
>>> from mechanize._html import CachingGeneratorFunction
>>> i = [1]
>>> func = CachingGeneratorFunction(i)
>>> list(func())
[1]
>>> list(func())
[1]
>>> i = [1, 2, 3]
>>> func = CachingGeneratorFunction(i)
>>> list(func())
[1, 2, 3]
>>> i = func()
>>> i.next()
1
>>> i.next()
2
>>> i.next()
3
>>> i = func()
>>> j = func()
>>> i.next()
1
>>> j.next()
1
>>> i.next()
2
>>> j.next()
2
>>> j.next()
3
>>> i.next()
3
>>> i.next()
Traceback (most recent call last):
...
StopIteration
>>> j.next()
Traceback (most recent call last):
...
StopIteration
Link text parsing
>>> def get_first_link_text_bs(html):
... factory = RobustLinksFactory()
... soup = MechanizeBs("utf-8", html)
... factory.set_soup(soup, "http://example.com/", "utf-8")
... return list(factory.links())[0].text
>>> def get_first_link_text_sgmllib(html):
... factory = LinksFactory()
... response = test_html_response(html)
... factory.set_response(response, "http://example.com/", "utf-8")
... return list(factory.links())[0].text
Whitespace gets compressed down to single spaces. Tags are removed.
>>> html = ("""\
... <html><head><title>Title</title></head><body>
... <p><a href="http://example.com/">The quick\tbrown fox jumps
... over the <i><b>lazy</b></i> dog </a>
... </body></html>
... """)
>>> get_first_link_text_bs(html)
'The quick brown fox jumps over the lazy dog'
>>> get_first_link_text_sgmllib(html)
'The quick brown fox jumps over the lazy dog'
Empty <a> links have empty link text
>>> html = ("""\
... <html><head><title>Title</title></head><body>
... <p><a href="http://example.com/"></a>
... </body></html>
... """)
>>> get_first_link_text_bs(html)
''
>>> get_first_link_text_sgmllib(html)
''
But for backwards-compatibility, empty non-<a> links have None link text
>>> html = ("""\
... <html><head><title>Title</title></head><body>
... <p><frame src="http://example.com/"></frame>
... </body></html>
... """)
>>> print get_first_link_text_bs(html)
None
>>> print get_first_link_text_sgmllib(html)
None
Title parsing. We follow Firefox's behaviour with regard to child
elements (haven't tested IE).
>>> def get_title_bs(html):
... factory = RobustTitleFactory()
... soup = MechanizeBs("utf-8", html)
... factory.set_soup(soup, "utf-8")
... return factory.title()
>>> def get_title_sgmllib(html):
... factory = TitleFactory()
... response = test_html_response(html)
... factory.set_response(response, "utf-8")
... return factory.title()
>>> html = ("""\
... <html><head>
... <title>Title</title>
... </head><body><p>Blah.<p></body></html>
... """)
>>> get_title_bs(html)
'Title'
>>> get_title_sgmllib(html)
'Title'
>>> html = ("""\
... <html><head>
... <title> Ti<script type="text/strange">alert("this is valid HTML -- yuck!")</script>
... tle &&
... </title>
... </head><body><p>Blah.<p></body></html>
... """)
>>> get_title_bs(html)
'Ti<script type="text/strange">alert("this is valid HTML -- yuck!")</script> tle &&'
>>> get_title_sgmllib(html)
'Ti<script type="text/strange">alert("this is valid HTML -- yuck!")</script> tle &&'
No more tags after <title> used to cause an exception
>>> html = ("""\
... <html><head>
... <title>""")
>>> get_title_sgmllib(html)
''
|
