Python Tag.string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 string [as 别名]
 def apply_solution(self, flux_dict, color_map=default_color_map):
     self.object_styles.clear()
     fluxes = dict((i, flux_dict[i]) for i in self.included_reactions.intersection(flux_dict))
     abs_fluxes = [min(abs(i), 20) for i in fluxes.itervalues()]
     x_min = min(abs_fluxes)
     x_max = max(abs_fluxes)
     scale_func = lambda value: min(1, (abs(value) - x_min) / (x_max - x_min) * 3)
     for reaction, value in fluxes.iteritems():
         #t = Tag(name="title")
         #t.string = "%.2f" % (value)
         self._rxn_layer.findChild("g", id=reaction).title.string += "\n%.2f" % (value)#append(t)
         try:
             t = Tag(name="title")
             t.string = "%.2f" % (value)
             self._rxn_label_layer.findChild(name="text", text=compile(reaction)).append(t)
         except: None
         if str(reaction) in self.included_reactions:
             self.set_object_color(str(reaction), color_map(scale_func(value)))
         if value < 0:
             self.object_styles["%s .end" % str(reaction)] = {"marker-end": "none"}
         if value > 0:
             self.object_styles["%s .start" % str(reaction)] = {"marker-start": "none"}
     for reaction in self.included_reactions.difference(flux_dict.keys()):
         self.set_object_color(reaction, (0, 0, 0))
     self._update_svg()
     return self

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
def makeTag(name, string=None, **kwargs):
    tag = Tag(name=name, attrs=kwargs)
    for key in kwargs:
        if kwargs[key] is None:
            kwargs[key] = ""
    if string:
        tag.string = string
    return tag

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
def putback_elems(source, elems, xml_elem):
	for elem in elems:
		if isinstance(elem, tuple):
			attr = elem[0]
			tag = elem[1]
		else:
			attr = elem
			tag = elem

		if hasattr(source, attr):
			e = Tag(name = tag)
			e.string = getattr(source, attr)
			xml_elem.append(e)

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
def transform_item_in_feed(item):
    """Transform an <item>"""

    link = item.link.text
    print('Processing {}'.format(link))

    # Ignore empty articles
    if item.description is None or len(item.description.contents) == 0:
        print('Empty article body, ignoring...')
        item.decompose()
        return

    # Ignore articles without title
    if item.title is None or len(item.title) == 0:
        print('Article without title, ignoring...')
        item.decompose()
        return

    # Parse the article content as HTML
    article = read_html_from_string(item.description.contents[0])

    # The creator in the RSS is a username, so try first to parse from the HTML.
    html_authors = _parse_article_authors(article)

    if html_authors is not None:
        item.creator.string = html_authors
        # Remove authors from article text itself
        article.find('div', class_='field-name-field-auteurs').decompose()

    # Get the category
    category_tag = Tag(name='category')
    category_node = article.select_one('div.field-name-field-rubriek a')

    if category_node is not None:
        category_tag.string = category_node.text.strip()
        category_tag['domain'] = category_node['href']
        # Remove category from the article body
        article.find('div', class_='field-name-field-rubriek').decompose()

    item.append(category_tag)

    # Remove edition from article body if present
    edition_node = article.find('div', class_='field-name-field-editie')
    if edition_node is not None:
        edition_node.decompose()

    encoded = article.find('body').decode_contents(formatter='html')
    item.description.contents = [CData(htmlmin.minify(encoded, remove_optional_attribute_quotes=False))]

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
def home():
	if request.method == "GET":
		return render_template("scrapermaker_form.html")

	elif request.method == "POST":
		url = request.form['url']
		r = requests.get(url)
		bs = BeautifulSoup(r.content)
		js_tag = Tag(bs, name="script")


		js_tag.string = payload
		body = bs.find("body")
		body.append(js_tag)

		return str(bs)

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
        ### the id of the parents is identical to the documentation_units
        # TODO: this is a dirty way and needs to be improved
        all_parents = find_parents(
            methods + functions + attributes + classmethods + staticmethods + sections + classes +
            exceptions + describtions + datas)
        all_parents_copy = copy.copy(all_parents)

        ###define placeholder and replace nested elements to avoid double rating
        placeholder = '[something removed here]'
        for parent in methods + functions + attributes + classmethods + staticmethods + sections + classes\
                + exceptions + describtions:
            ### set placeholders to duplicated dl-elements ###
            for elem in parent.find_all('dl', {
            'class': ['method', 'function', 'attribute', 'classmethod', 'staticmethod', 'section', 'class', 'exception', 'describe', 'data']}):
                tag = Tag(name='p')
                tag.string = placeholder
                elem.replace_with(tag)
            ### same thing with sections##
            for elem in parent.find_all('div', {'class': 'section'}):
                tag = Tag(name='p')
                tag.string = placeholder
                elem.replace_with(tag)

            ### summarize placeholders ###
            summarize_placeholders(parent, placeholder)

        results = methods + functions + attributes + classmethods + staticmethods + sections + classes \
                  + exceptions + describtions + datas

        # # #########STORE SOMETHING INTO THE DATABASE#############
        conn = psycopg2.connect("host=127.0.0.1 dbname=mydb user=sven password=Schwen91")

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
# make sidebar for chapters
#----------------------------------------------------- 

for idx, chapter in enumerate(chapterDicts): 
	soup = Soup()

	soupFromFile = Soup(open(chapter['destChapterPath']).read())

	# Create previous/next links in the footer
	nextChapterDiv = soupFromFile.find(id='next_chapter')
	prevChapterDiv = soupFromFile.find(id='prev_chapter')

	if (idx != 0):
		prevLink = Tag(soup, None, "a")
		prevLink['href'] = chapterDicts[idx-1]['href']
		prevLink.string = "< " + chapterDicts[idx-1]['title'] 
		prevChapterDiv.append(prevLink)
	

	if(idx != len(chapterDicts)-1):
		nextLink = Tag(soup, None, "a")
		nextLink['href'] = chapterDicts[idx+1]['href']
		nextLink.string = chapterDicts[idx+1]['title'] + " >"		
		nextChapterDiv.append(nextLink)
	
	
	# Find the navbar UL
	navbar = soupFromFile.find_all("ul", {"id":"nav-parts"})[0]


	# Run through the chapter groups

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
# table.append(tr)
# 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"

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
def format_links(html):
    '''
    This monster of a function takes in the html from a post and returns a dict
        containing html, text, summary.
    Uses opengraph to try to get titles for all untitled links, and tries to hyperlink everything.
    '''
    edit_html = html
    html = html.replace('"', '"')
    soup = BeautifulSoup(re.sub(r'&(?!amp;)', r'&', html))

    reformat_str = ''.join(random.sample(string.ascii_uppercase, 10)) + '__'
    reformat_dict = {}
    videos = []
    image = None

    # Set aside all <img> tags, because we need to treat them special and will add them in later.
    for tag_index, img_tag in enumerate(soup.find_all('img')):
        key = reformat_str + 'img' + str(tag_index)
        img_tag.replace_with(key)

        # handle the shitty case where a user inputs a non-http link
        if img_tag.has_attr('src') and not img_tag['src'].startswith('http'):
            new_src = 'http://' + img_tag['src']
            img_tag['src'] = new_src
        if not image:
            image = img_tag['src']

        reformat_dict[key] = img_tag

    # Set aside all <a> tags, because we need to treat them special and will add them in later.
    for tag_index, a_tag in enumerate(soup.find_all('a')):
        key = reformat_str + 'a' + str(tag_index)
        a_tag.replace_with(key)

        # handle the shitty case where a user inputs a non-http link
        if a_tag.has_attr('href'):
            new_href = a_tag['href'].strip()
            if not new_href.startswith('http'):
                new_href = 'http://' + a_tag['href']
            a_tag['href'] = new_href
            embed_link = get_embed_link(new_href)
            if embed_link:
                videos.append(embed_link)

        a_tag['target'] = '_blank'

        try:
            if a_tag.string and a_tag['href'] and a_tag.string in a_tag['href']:
                og_title = get_opengraph(a_tag['href'], params=['title']).get('title')
                a_tag.string = og_title.strip()
        except:
            pass

        reformat_dict[key] = a_tag

    mentions = []
    # Find all mentions and format them
    mention_regex = re.compile(r'(@\S+(?:\s\S+)?)')
    for mention_index, mention_str in enumerate(soup(text=mention_regex)):
        key = reformat_str + 'm' + str(mention_index)
        mention_split_list = mention_regex.split(mention_str)
        parent_tag = Tag(name='span')

        for piece in mention_split_list:
            if type(piece) in [unicode, str]:
                s = mention_regex.search(piece)
                if s:
                    first_letter = re.search(r"@\S+", piece).group()[1]
                    names = [u.name for u in User.objects(name__istartswith=first_letter)]
                    for i in range(len(piece) - 1):
                        query_name = re.compile(piece[1:len(piece) - i], flags=re.IGNORECASE)
                        matches = len([name for name in names if query_name.match(name)])
                        if matches == 1:
                            a_tag = Tag(name='a')
                            target_user = User.objects(name=query_name).get()
                            a_tag['href'] = '/profile/%s' % str(target_user.id)
                            a_tag['target'] = '_blank'
                            a_tag['mention'] = 'Yes'
                            a_tag.string = '@' + query_name.pattern
                            parent_tag.append(a_tag)
                            parent_tag.append(NavigableString(piece[len(piece) - i:]))
                            mentions.append(str(target_user.id))
                            break
                    else:
                        # for/else structure
                        # catch an @ that didn't match any users
                        parent_tag.append(NavigableString(piece))
                else:
                    parent_tag.append(NavigableString(piece))

        reformat_dict[key] = parent_tag
        mention_str.replace_with(key)

    opengraph_index = 0
    opengraph_objects = []

    # Find all plaintext links and format them.
    for p in soup.find_all('p'):
        p_text = unicode(p.text)
        if link_regex.search(p_text):
#.........这里部分代码省略.........

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
# make sidebar for chapters
#-----------------------------------------------------

for idx, chapter in enumerate(chapterDicts):
	soup = Soup()

	soupFromFile = Soup(open(chapter['destChapterPath'], "rb").read(), "html.parser")

	# Create previous/next links in the footer
	nextChapterDiv = soupFromFile.find(id='next_chapter')
	prevChapterDiv = soupFromFile.find(id='prev_chapter')

	if (idx != 0):
		prevLink = Tag(soup, None, "a")
		prevLink['href'] = chapterDicts[idx-1]['href']
		prevLink.string = "< " + chapterDicts[idx-1]['title']
		prevChapterDiv.append(prevLink)


	if(idx != len(chapterDicts)-1):
		nextLink = Tag(soup, None, "a")
		nextLink['href'] = chapterDicts[idx+1]['href']
		nextLink.string = chapterDicts[idx+1]['title'] + " >"
		nextChapterDiv.append(nextLink)


	# Find the navbar UL
	navbar = soupFromFile.find_all("ul", {"id":"nav-parts"})[0]


	# Run through the chapter groups

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
 def text_tag(self):
     t=Tag(name='span')
     t['class']=self.cls+['n']
     t.string=self.text
     return t

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [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()

# 需要导入模块: from bs4 import Tag [as 别名]
# 或者: from bs4.Tag import string [as 别名]
def new_tag(tag, string):
    t = Tag(name=tag)
    t.string = string
    return t