Python Tag.append方法代码示例

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
 def construct_xml(self):
     soup = BeautifulSoup(etree.tostring(etree.Element('OTA_AirLowFareSearchRQ')), 'xml')
     query = soup.contents[0]
     query.attrs = {
         'xmlns':'http://www.opentravel.org/OTA/2003/05',
         'xmlns:xsi':'http://www.w3.org/2001/XMLSchema-instance',
         'PrimaryLangId':'en',
         'Version':'2.001',
         'TimeStamp':str(datetime.datetime.now().isoformat()),
         'EchoToken':str(time.mktime(time.gmtime())),
         'xsi:schemaLocation':'http://www.opentravel.org/2006A/OTA_AirLowFareSearchRQ.xsd',
     }
     
     t_pos = Tag(name='POS')
     t_source = Tag(name='Source')
     t_req = Tag(name='RequestorID')
     t_req.attrs = {
         'ID':'weathersick',
         'URL':'http://www.weathersick.com',
         'Type':'18',
     }
     t_source.append(t_req)
     t_pos.append(t_source)
     query.append(t_pos)
     
     t_odinf = Tag(name='OriginDestinationInformation')
     t_odinf.attrs {'RPH':1}
     t_deptime = Tag(name='DepartureDateTime')
     t_deptime.
     
     OriginDestinationInformation RPH="1"
     
     import pdb; pdb.set_trace()

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def heading2table(soup, table, row):
    """add heading row to table"""
    tr = Tag(soup, name="tr")
    table.append(tr)
    for attr in row:
        th = Tag(soup, name="th")
        tr.append(th)
        th.append(attr)

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def row2table(soup, table, row):
    """ad a row to the table"""
    tr = Tag(soup, name="tr")
    table.append(tr)
    for attr in row:
        td = Tag(soup, name="td")
        tr.append(td)
        td.append(attr)

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
 def tag(self):
     tt=Tag(name='table')
     for r in self.cells:
         rt=Tag(name='tr')
         for c in r:
             rt.append(c.tag())
         tt.append(rt)
     return tt

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def replace_dot_code(dot_code: Tag) -> None:
    svg = BeautifulSoup(dot(dot_code.text), 'xml').svg
    assert 'style' not in svg.attrs
    svg.attrs['style'] = (
        f'max-width: 100%; '
        f'width: {svg.attrs.pop("width")}; '
        f'height: {svg.attrs.pop("height")};'
    )
    dot_code.clear()
    dot_code.append(svg)

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def clone(el):
    if isinstance(el, NavigableString):
        return type(el)(el)

    copy = Tag(None, el.builder, el.name, el.namespace, el.nsprefix)
    # work around bug where there is no builder set
    # https://bugs.launchpad.net/beautifulsoup/+bug/1307471
    copy.attrs = dict(el.attrs)
    for attr in ('can_be_empty_element', 'hidden'):
        setattr(copy, attr, getattr(el, attr))
    for child in el.contents:
        copy.append(clone(child))
    return copy

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
 def soup(self):
     '''
         Returns HTML as a BeautifulSoup element.
     '''
     components_soup = Tag(name=self.tagname, builder=BUILDER)
     components_soup.attrs = self.attributes
     for c in flatten(self.components):
         if hasattr(c, 'soup'):
             components_soup.append(c.soup())
         elif type(c) in (str, ):
             # components_soup.append(BeautifulSoup(str(c)))
             components_soup.append(str(c))
         # else:
             # Component should not be integrated
             # pass
     return components_soup

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def clone_bs4_elem(el):
    """Clone a bs4 tag before modifying it.

    Code from `http://stackoverflow.com/questions/23057631/clone-element-with
    -beautifulsoup`
    """
    if isinstance(el, NavigableString):
        return type(el)(el)

    copy = Tag(None, el.builder, el.name, el.namespace, el.nsprefix)
    # work around bug where there is no builder set
    # https://bugs.launchpad.net/beautifulsoup/+bug/1307471
    copy.attrs = dict(el.attrs)
    for attr in ('can_be_empty_element', 'hidden'):
        setattr(copy, attr, getattr(el, attr))
    for child in el.contents:
        copy.append(clone_bs4_elem(child))
    return copy

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def get_markdown_page_index_objects(content: Tag, url: str, page_path: str, title: str, page_type: str,
                                    page_views: int) -> List[Dict]:
    headers = ['h1', 'h2', 'h3']
    index_objects = []
    children = [element for element in content.children if isinstance(element, Tag)]
    if children[0].name not in headers:
        return get_page_index_objects(content, url, page_path, title, page_type, page_views)
    block_title = ""
    content = []
    url_with_href = ""
    for child in children:
        if child.name in headers:
            if block_title != '':
                for ind, page_part in enumerate(get_valuable_content(content)):
                    page_info = {'url': url_with_href, 'objectID': url_with_href + str(ind), 'content': page_part,
                                 'headings': block_title, 'pageTitle': title, 'type': page_type,
                                 'pageViews': page_views}
                    index_objects.append(page_info)
            url_with_href = url + '#' + child.get('id')
            block_title = child.text
            content = []
        else:
            content.append(child)
    return index_objects

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def printhtml(csvdiffs):
    """print the html"""
    soup = BeautifulSoup()
    html = Tag(soup, name="html")
    para1 = Tag(soup, name="p")
    para1.append(csvdiffs[0][0])
    para2 = Tag(soup, name="p")
    para2.append(csvdiffs[1][0])
    table = Tag(soup, name="table")
    table.attrs.update(dict(border="1"))

    soup.append(html)
    html.append(para1)
    html.append(para2)
    html.append(table)
    heading2table(soup, table, csvdiffs[3])
    for row in csvdiffs[4:]:
        row = [str(cell) for cell in row]
        row2table(soup, table, row)
    # print soup.prettify()
    print(soup)    

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def _extract_article_body(page):
    article = page.find(id='artikel').find(class_='content')

    body = Tag(name='temporary_tag')

    # +1 internetz for the person who can tell me why I can't write:
    #   for element in article.children:
    # or
    #   for element in article.contents:
    for element in list(article.children):
        # Ignore the comment form
        if element.name == 'form':
            continue

        # Ignore whitespace
        if element.name is None and re.search('\S', str(element)) is None:
            continue

        # Nor div, nor form, nor whitespace: probably article content
        if element.name != 'div':
            body.append(element.extract())
            continue

        # TODO uncomment me when the app is ready to support subtitles
        # Oh, and change the next if with an elif
        #  if 'field-field-ondertitel' in element['class']:
        #      paragraph = _extract_paragraph(element, 'subtitle')
        #      body.append(paragraph)

        if 'field-field-inleiding' in element['class']:
            paragraph = _extract_paragraph(element, 'introduction')
            body.append(paragraph)

        elif 'field-field-img-regulier' in element['class']:
            images_div = Tag(name='div', attrs={'class': 'image'})
            for image_and_caption in element(id='image-and-caption'):
                image = image_and_caption.img
                caption = image_and_caption.find(class_='caption-text')

                paragraph = Tag(name='p')
                paragraph.append(image)
                if caption is not None:
                    paragraph.append(caption.text)

                images_div.append(paragraph)
            body.append(images_div)

        elif 'field-field-website' in element['class']:
            label = element.find(class_='field-label').text
            label_p = Tag(name='p')
            label_s = Tag(name='strong')
            label_s.append(label)
            label_p.append(label_s)
            body.append(label_p)

            websites = element.find(class_='field-item').contents
            for website in list(websites):
                body.append(website)

        else:
            # Ignore other divs
            pass

    return body

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
			for fig in divFigures:
						
				figCaption = fig.p
				# Turn the caption into span for CSS formatting

				#note the games chapter needs some caption work
				if figCaption is not None: 
					figCaption.name = "div"

				# [zach] -- this is to make images that are not full width, have captions below the image
				
				div = Tag(soup, None, "div")
				
				div['style'] = "image" #"clear:both"
				
				div.append(clone(fig.img))
				
				fig.img.replace_with(div)
				# Images have been stored in ./CHAPTER_NAME/images/ relative 
				# to the chapter html, but image references in the html are 
				# to ./images/.  Modify the image tags:
				div.img["src"] = internalImagesPath + "/" + div.img["src"]
				# Turn the figure image into a hyperlink that points to the
				# full resolution version of the image
				imgHyperlink = soup.new_tag("a", href=fig.img["src"])
				fig.img.wrap(imgHyperlink)


				fig['class'] = "inner"
				divWhole = Tag(soup, None, "div")
				divWhole['class'] = "figure"

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
# for attr in mem_attr:
#     th = Tag(soup, None, "th")
#     tr.append(th)
#     th.append(attr)
# print soup.prettify()




for c in chapterTags: 
	ul = Tag(soup, None, "ul")
	li = Tag(soup, None, "li")
	a = Tag(soup, None, "a");
	a['href'] = "chapters/" + c['path'] + ".html"
	a.string = c['title']
	li.append(a)
	ul.append(li)

	#print c['title']
	#print c['path']
	if (len(['innerTags'])):
		ulInner = Tag(soup, None, "ul")
		li.append(ulInner);
		for tag in c['innerTags']: 
			liInner = Tag(soup, None, "li")
			ulInner.append(liInner)
			a = Tag(soup, None, "a")
			tagNoSpaces = tag.replace(" ", "")
			a['href'] = "chapters/" + c['path'] + ".html#" + tagNoSpaces
			a['target'] = "_top"
			a.string = tag

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
		if len(divFigures) != 0:
			
			for fig in divFigures:
				
				figCaption = fig.p
				# Turn the caption into span for CSS formatting

				#note the games chapter needs some caption work
				if figCaption is not None: 
					figCaption.name = "span"

				# [zach] -- this is to make images that are not full width, have captions below the image
				
				div = Tag(soup, None, "div")
				div['style'] = "clear:both"
				div.append(clone(fig.img));
				
				fig.img.replace_with(div)
				# Images have been stored in ./CHAPTER_NAME/images/ relative 
				# to the chapter html, but image references in the html are 
				# to ./images/.  Modify the image tags:
				div.img["src"] = internalImagesPath + "/" + div.img["src"]
		
		# Make all hyperlinks in the chapter target a new window/tab
		hyperlinkTags = soup.find_all("a")
		for hyperlinkTag in hyperlinkTags:
			hyperlinkTag["target"]= "_blank"

		html = str(soup)
		with open(destChapterPath, "wb") as file:
			file.write(html)

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import append [as 别名]
def rebuild_rss(url, output, selectors, replace = None, pretty = False, raw = False):
	source = feedparser.parse(url)

	try:
		soup = BeautifulSoup('<rss version="2.0" />', 'xml')
		rss = soup.rss
		has_lxml = True
	except FeatureNotFound:
		rss = BeautifulSoup('<rss version="2.0" />').rss
		has_lxml = False

	channel = Tag(name = 'channel')
	rss.append(channel)
	putback_elems(source.feed, channel_required, channel)
	putback_elems(source.feed, channel_optional, channel)

	build_date = Tag(name = 'lastBuildDate')
	build_date.string = time.strftime('%a, %d %b %Y %H:%M:%S +0000', time.gmtime())
	channel.append(build_date)

	generator = Tag(name = 'generator')
	generator.string = source.feed.generator + ' & RSS Rebuilder' if hasattr(source.feed, 'generator') else 'RSS Rebuilder'
	channel.append(generator)

	if replace:
		regexp = re.compile(replace[0])

	for entry in source.entries:
		item = Tag(name = 'item')
		channel.append(item)

		putback_elems(entry, item_required, item)
		putback_elems(entry, item_optional, item)

		r = requests.get(entry.link)
		html = r.content if raw else r.text
		linked_html = BeautifulSoup(html, 'lxml') if has_lxml else BeautifulSoup(html)

		content = ''
		for selector in selectors:
			tags = linked_html.select(selector)
			if replace:
				tags = replace_urls(tags, regexp, replace[1])

			content = reduce(lambda s, tag: s + unicode(tag), tags, content)

		desc = Tag(name = 'description')
		desc.string = content
		item.append(desc)

	out_func = lambda x: (x.prettify() if pretty else unicode(x)).encode('utf-8')
	if output == '-':
		out_file = sys.stdout
		close_file = lambda: None
	else:
		out_file = open(output, 'w')
		close_file = out_file.close

	if has_lxml:
		out_file.write(out_func(soup))
	else:
		out_file.write('<?xml version="1.0" encoding="UTF-8" ?>\n')
		out_file.write(out_func(rss))
	out_file.write('\n')
	close_file()