diff options
Diffstat (limited to 'BeautifulSoup.py')
| -rw-r--r-- | BeautifulSoup.py | 91 |
1 files changed, 45 insertions, 46 deletions
diff --git a/BeautifulSoup.py b/BeautifulSoup.py index 3a25207..1427ad2 100644 --- a/BeautifulSoup.py +++ b/BeautifulSoup.py @@ -1218,6 +1218,51 @@ class XMLParserBuilder(HTMLParser, TreeBuilder): class HTMLParserBuilder(XMLParserBuilder): + """This builder knows the following facts about HTML: + + * Some tags have no closing tag and should be interpreted as being + closed as soon as they are encountered. + + * The text inside some tags (ie. 'script') may contain tags which + are not really part of the document and which should be parsed + as text, not tags. If you want to parse the text as tags, you can + always fetch it and parse it explicitly. + + * Tag nesting rules: + + Most tags can't be nested at all. For instance, the occurance of + a <p> tag should implicitly close the previous <p> tag. + + <p>Para1<p>Para2 + should be transformed into: + <p>Para1</p><p>Para2 + + Some tags can be nested arbitrarily. For instance, the occurance + of a <blockquote> tag should _not_ implicitly close the previous + <blockquote> tag. + + Alice said: <blockquote>Bob said: <blockquote>Blah + should NOT be transformed into: + Alice said: <blockquote>Bob said: </blockquote><blockquote>Blah + + Some tags can be nested, but the nesting is reset by the + interposition of other tags. For instance, a <tr> tag should + implicitly close the previous <tr> tag within the same <table>, + but not close a <tr> tag in another table. + + <table><tr>Blah<tr>Blah + should be transformed into: + <table><tr>Blah</tr><tr>Blah + but, + <tr>Blah<table><tr>Blah + should NOT be transformed into + <tr>Blah<table></tr><tr>Blah + + Differing assumptions about tag nesting rules are a major source + of problems with the BeautifulSoup class. If BeautifulSoup is not + treating as nestable a tag your page author treats as nestable, + try subclassing this tree builder or using another parser's tree + builder.""" assume_html = True PRESERVE_WHITESPACE_TAGS = set(['pre', 'textarea']) @@ -1534,52 +1579,6 @@ class BeautifulStoneSoup(Tag): class BeautifulSoup(BeautifulStoneSoup): - """This parser knows the following facts about HTML: - - * Some tags have no closing tag and should be interpreted as being - closed as soon as they are encountered. - - * The text inside some tags (ie. 'script') may contain tags which - are not really part of the document and which should be parsed - as text, not tags. If you want to parse the text as tags, you can - always fetch it and parse it explicitly. - - * Tag nesting rules: - - Most tags can't be nested at all. For instance, the occurance of - a <p> tag should implicitly close the previous <p> tag. - - <p>Para1<p>Para2 - should be transformed into: - <p>Para1</p><p>Para2 - - Some tags can be nested arbitrarily. For instance, the occurance - of a <blockquote> tag should _not_ implicitly close the previous - <blockquote> tag. - - Alice said: <blockquote>Bob said: <blockquote>Blah - should NOT be transformed into: - Alice said: <blockquote>Bob said: </blockquote><blockquote>Blah - - Some tags can be nested, but the nesting is reset by the - interposition of other tags. For instance, a <tr> tag should - implicitly close the previous <tr> tag within the same <table>, - but not close a <tr> tag in another table. - - <table><tr>Blah<tr>Blah - should be transformed into: - <table><tr>Blah</tr><tr>Blah - but, - <tr>Blah<table><tr>Blah - should NOT be transformed into - <tr>Blah<table></tr><tr>Blah - - Differing assumptions about tag nesting rules are a major source - of problems with the BeautifulSoup class. If BeautifulSoup is not - treating as nestable a tag your page author treats as nestable, - try ICantBelieveItsBeautifulSoup, MinimalSoup, or - BeautifulStoneSoup before writing your own subclass.""" - def _defaultBuilder(self): return HTMLParserBuilder() |