import re
comments = soup.findAll(text=lambda text:isinstance(text, Comment))
for comment in comments:
e = re.match(r'<i>([^<]*)</i>', comment.string).group(1)
print e
from pyparsing import makeHTMLTags, oneOf, withAttribute, Word, nums, Group, htmlComment
import calendar
# have pyparsing define tag start/end expressions for the
# tags we want to look for inside the comments
span,spanEnd = makeHTMLTags("span")
i,iEnd = makeHTMLTags("i")
# only want spans with class=titlefont
span.addParseAction(withAttribute(**{'class':'titlefont'}))
# define what specifically we are looking for in this comment
weekdayname = oneOf(list(calendar.day_name))
integer = Word(nums)
dateExpr = Group(weekdayname("day") + integer("daynum"))
commentBody = '<!--' + span + i + dateExpr("date") + iEnd
# define a parse action to attach to the standard htmlComment expression,
# to extract only what we want (or raise a ParseException in case
# this is not one of the comments we're looking for)
def grabCommentContents(tokens):
return commentBody.parseString(tokens[0])
htmlComment.addParseAction(grabCommentContents)
# let's try it
htmlsource = """
want to match this one
<!-- <span class="titlefont"> <i>Wednesday 110518</i>(05:00PM)<br /></span> -->
don't want the next one, wrong span class
<!-- <span class="bodyfont"> <i>Wednesday 110519</i>(05:00PM)<br /></span> -->
not even a span tag!
<!-- some other text with a date in italics <i>Wednesday 110520</i>(05:00PM)<br /></span> -->
another matching comment, on a different day
<!-- <span class="titlefont"> <i>Thursday 110521</i>(05:00PM)<br /></span> -->
"""
for comment in htmlComment.searchString(htmlsource):
parsedDate = comment.date
# date info can be accessed like elements in a list
print parsedDate[0], parsedDate[1]
# because we named the expressions within the dateExpr Group
# we can also get at them by name (this is much more robust, and
# easier to maintain/update later)
print parsedDate.day
print parsedDate.daynum
print
您可以通过
findAll
方法在文档中找到所有注释。请参见下面的示例,该示例演示如何准确地执行您要执行的操作Removing elements:简而言之,您需要:
编辑:如果要在列中搜索,可以尝试:
Pyparsing允许您使用内置的
htmlComment
表达式搜索HTML注释,并附加parse time回调来验证和提取注释中的各种数据字段:印刷品:
相关问题 更多 >
编程相关推荐