Python html.remove_tags函数代码示例

	def parse(self, response):
		ts = time.time()
		html_name = 'txt/artist/artist' + str(ts) + '.txt'
		file = codecs.open(html_name, 'w+', 'utf-8')
		
		# file.write(response.url)
		# file.write('\n')

		for body in response.css('div.layoutSingleColumn h3').extract():
			body = body.encode(response.encoding)
			body = remove_tags(body)
			print "Header"
			print(body)
			try:
				file.write(body)
			except AttributeError:
				print(AttributeError)
				sys.exit(0)

		for body in response.css('div.layoutSingleColumn p').extract():
			body = body.encode(response.encoding)
			body = remove_tags(body)
			print "Paragraph"
			print(body)
			try:
				file.write(body)
			except AttributeError:
				print(AttributeError)
				sys.exit(0)

		file.close()

    def test_remove_tags(self):
        # text with tags
        self.assertEqual(remove_tags(u'<p>one p tag</p>'), u'one p tag')
        self.assertEqual(remove_tags(u'<p>one p tag</p>', which_ones=('b',)), u'<p>one p tag</p>')

        self.assertEqual(remove_tags(u'<b>not will removed</b><i>i will removed</i>', which_ones=('i',)),
                         u'<b>not will removed</b>i will removed')

	def parse(self, response):
		max_position = ''
		koma = ','
		headers = response.headers
		itemselector = Selector(response).xpath('//div[@class="content"]')

		if headers['Content-Type'] == 'application/json;charset=utf-8':
			data = json.loads(response.body)
			itemselector = Selector(text=data['items_html']).xpath('//div[@class="content"]')
			max_position = data['min_position']
			yield Request("https://twitter.com/i/search/timeline?f=tweets&vertical=default&q=%22demam%20berdarah%22%20OR%20dbd%20OR%20dhf%20OR%20%22dengue%20fever%22%20OR%20%22dengue%20hemorrhagic%22%20OR%20%22sakit%20db%22%20lang%3Aid%20since%3A"+self.start+"%20until%3A"+self.end+"&src=typd&include_available_features=1&include_entities=1&max_position="+max_position+"&reset_error_state=false", 
					callback=self.parse, 
					method="GET",)
		
		for sel in itemselector:
			self.index += 1
			item = TwitterscrapingItem()
			item['index'] = self.index
			item['userid'] = ''.join(
				map(unicode.strip, sel.xpath('div[@class="stream-item-header"]/a/@data-user-id').extract()))
			item['username'] = ''.join(
				map(unicode.strip, sel.xpath('div[@class="stream-item-header"]/a/span[@class="username js-action-profile-name"]/b/text()').extract()))
			item['fullname'] = ''.join(
				map(unicode.strip, sel.xpath('div[@class="stream-item-header"]/a/strong/text()').extract()))
			text_tweet = ''.join(
				map(unicode.strip, sel.xpath('p[@class="TweetTextSize  js-tweet-text tweet-text"]').extract()))
			item['text_tweet'] = remove_tags(text_tweet).replace('\n',' ').replace('\u',' ')
			item['original_text_tweet'] = text_tweet
			hash_tags = koma.join(
				map(unicode.strip, sel.xpath('p[@class="TweetTextSize  js-tweet-text tweet-text"]'
					'/a[@class="twitter-hashtag pretty-link js-nav"]').extract()))
			item['hash_tags'] = remove_tags(hash_tags)
			item['time_tweet'] = ''.join(
				map(unicode.strip, sel.xpath('div[@class="stream-item-header"]/small[@class="time"]/a/@title').extract()))
			item['lang'] = ''.join(
				map(unicode.strip, sel.xpath('p[@class="TweetTextSize  js-tweet-text tweet-text"]/@lang').extract()))
			retweets = ''.join(
				map(unicode.strip, sel.xpath('div[@class="stream-item-footer"]'
					'/div[@class="ProfileTweet-actionList js-actions"]'
					'/div[@class="ProfileTweet-action ProfileTweet-action--retweet js-toggleState js-toggleRt"]'
					'/button[@class="ProfileTweet-actionButton  js-actionButton js-actionRetweet"]'
					'/div[@class="IconTextContainer"]').extract()))
			item['retweets'] = remove_tags(retweets).strip()
			favorite = ''.join(
				map(unicode.strip, sel.xpath('div[@class="stream-item-footer"]'
					'/div[@class="ProfileTweet-actionList js-actions"]'
					'/div[@class="ProfileTweet-action ProfileTweet-action--favorite js-toggleState"]'
					'/button[@class="ProfileTweet-actionButton js-actionButton js-actionFavorite"]'
					'/div[@class="IconTextContainer"]').extract()))
			item['favorite'] = remove_tags(favorite).strip()
			item['place_id'] = ''.join(
				map(unicode.strip, sel.xpath('div[@class="stream-item-header"]/span[@class="Tweet-geo u-floatRight js-tooltip"]/a/@data-place-id').extract()))	
			item['place'] = ''.join(
				map(unicode.strip, sel.xpath('div[@class="stream-item-header"]/span[@class="Tweet-geo u-floatRight js-tooltip"]/a/span[@class="u-hiddenVisually"]/text()').extract()))	
			item['max_position'] = max_position

			yield item

 def test_returns_unicode(self):
     # make sure it always return unicode
     assert isinstance(remove_tags(b'no tags'), six.text_type)
     assert isinstance(remove_tags(b'no tags', which_ones=('p',)), six.text_type)
     assert isinstance(remove_tags(b'<p>one tag</p>'), six.text_type)
     assert isinstance(remove_tags(b'<p>one tag</p>', which_ones=('p')), six.text_type)
     assert isinstance(remove_tags(b'<a>link</a>', which_ones=('b',)), six.text_type)
     assert isinstance(remove_tags(u'no tags'), six.text_type)
     assert isinstance(remove_tags(u'no tags', which_ones=('p',)), six.text_type)
     assert isinstance(remove_tags(u'<p>one tag</p>'), six.text_type)
     assert isinstance(remove_tags(u'<p>one tag</p>', which_ones=('p')), six.text_type)
     assert isinstance(remove_tags(u'<a>link</a>', which_ones=('b',)), six.text_type)

 def parse(self, response):
     hrefs = response.selector.xpath('//div[contains(@class, "c-container")]/h3/a/@href').extract()
     containers = response.selector.xpath('//div[contains(@class, "c-container")]')
     for container in containers:
         href = container.xpath('h3/a/@href').extract()[0]
         title = remove_tags(container.xpath('h3/a').extract()[0])
         c_abstract = container.xpath('div/div/div[contains(@class, "c-abstract")]').extract()
         abstract = ""
         if len(c_abstract) > 0:
             abstract = remove_tags(c_abstract[0])
         request = scrapy.Request(href, callback=self.parse_url)
         request.meta['title'] = title
         request.meta['abstract'] = abstract
         yield request

	def parse(self, response):
		s = Selector(response)
		next_link = s.xpath('//div[@class="w-button-more"]/a/@href').extract()
		if len(next_link):
			yield Request("https://mobile.twitter.com"+next_link[0], callback=self.parse)
		itemselector = Selector(response).xpath('//*[@id="main_content"]/div/div[3]/table')
		#regex = re.compile(r"([\\]+u\d*)", re.MULTILINE)
		for sel in itemselector:
			self.index += 1
			item = TwitterscrapingItem()
			item['index'] = self.index
			item['username'] = ''.join(
				map(unicode.strip, sel.xpath('tr[1]/td[2]/a/div/text()').extract()))
			tweet = remove_tags(''.join(
				map(unicode.strip, sel.xpath('tr[2]/td/div').extract()))
				).replace('&amp','&').replace('  ','').replace('\n      ','').replace('\n    ','').replace('\n','').replace('\u',' ')
			item['text_tweet'] = u''+tweet
			item['original_tweet'] = ''.join(sel.xpath('tr[2]/td/div/div').extract())
			item['time_tweet'] = ''.join(
				map(unicode.strip, sel.xpath('tr[1]/td[3]/a/text()').extract()))
			item['url'] = ''.join(
				map(unicode.strip, sel.xpath('tr[2]/td/div/@data-id').extract()))
			item['data_id'] = ''.join(
				map(unicode.strip, sel.xpath('tr[3]/td/span[1]/a/@href').extract()))
			yield item

 def _extract_features(self, sel, item):
     description_xpath = '//div[@id="tab1"]/ul/li'
     data = sel.xpath(description_xpath).extract()
     if len(data) > 0 :
         data = [remove_tags(v).strip().replace(' ',' ').replace('>','>').strip()  for v in data]
         data = filter(None,data)
         item['description'] = '<br>'.join(data)

    def parse_speech(self, response):
        paragraphs = response.css('p')[:-1]  # last p contains pagination
        text = remove_tags(''.join(paragraphs.extract()))

        l = ParlamentHuSpeechLoader(item=Speech(), selector=response,
            scheme='parlament.hu/people')
        l.add_value('text', text)
        l.add_value('type', 'speech')
        l.add_value('sources', [response.url])
        l.add_xpath('position', '//b[1]/text()')
        l.add_xpath('video', '//table//tr[6]//td[2]/a/@href')
        l.add_xpath('creator_id', '//table//tr[2]//td[2]/a/@href',
            re=r'ogy_kpv\.kepv_adat\?p_azon=(\w\d+)')
        l.add_value('event_id', response.meta['event_id'])

        date = response.xpath(
            '//table//tr[1]/th/text()').re(r'\d{4}\.\d{2}.\d{2}\.')
        time = response.meta.get('time')
        if date:
            date = date[0]
            if time:
                date += time[0]
            l.add_value('date', date)
        item = l.load_item()
        yield item
        if 'creator_id' in item:
            yield scrapy.Request(self.get_api_url(
                self.PERSON_ENDPOINT, params={
                    'p_azon': item['creator_id']['identifier']}),
                callback=self.parse_person, meta={
                    'p_azon': item['creator_id']['identifier']})

def make_it_clean(line):
	'''
	Очистка текста от тегов html, css стилей, js
	(string) line - входной текст
	'''
	cleari = remove_tags(line)
	soline = re.compile("(\<.+\n)", re.DOTALL)
	boline = re.compile("(.+\>)", re.DOTALL)
	alline = re.compile("\<.+\>", re.DOTALL)
	cleari = re.sub(soline, '', cleari)
	cleari = re.sub(boline, '', cleari)
	cssline = re.compile(r"\{.+\}{1}", re.DOTALL)
	cleari = re.sub(cssline, ' ', cleari)
	cleari = re.sub("async=\"async\"\n", '', cleari)
	cleari = re.sub("src=.+\"", '', cleari)
	cleari = re.sub("var\s_.+\)", '', cleari)
	cleari = re.sub("function.+\"\)", '', cleari)
	cleari = re.sub("document.+\);", " ", cleari)
	cleari = re.sub("function.+\)", " ", cleari)
	cleari = re.sub("&laquo;", " «", cleari)
	cleari = re.sub("&raquo;", "» ", cleari)
	cleari = re.sub("&rarr;", "→", cleari)
	cleari = re.sub(r'&nbsp;', ' ', cleari)
	cleari = re.sub(r'(&mdash;)|(&ndash;)', '-', cleari)
	cleari = re.sub(r'\t{2,}', ' ', cleari)
	cleari = re.sub(r'\s{2,}', ' ', cleari)
	cleari = re.sub(r'\n{2,}', '\n', cleari)
	cleari = re.sub(r"(\<\!\-\-.*\-\-\>)", '', cleari)

	return cleari

    def parse_item(self, response):

        province = response.css('.dqwz>a:last-child::attr(title)').re_first(ur'2017年(.+?)省?本科')
        school = response.css('.nr>h2::text').extract_first()
        count = len(response.xpath('//div[@id="ivs_content"]/table//tr[1]/td').extract())
        for row in response.xpath('//div[@id="ivs_content"]/table//tr[position()>1]'):
            fields = [remove_tags(i).strip() for i in row.css('td').extract()]
            if count == 4:
                del fields[0]
            if len(fields) == 3:
                rowspan_count = [e.css('::attr(rowspan)').extract_first(1) for e in row.css('td')][-3:]
                rowspan_value = fields
                rowspans = len([i for i in rowspan_count if i > 1])
            elif len(fields) + rowspans == 3:
                new_fields = []
                fields.reverse()
                for k, v in zip(rowspan_count, rowspan_value):
                    if k == 1:
                        new_fields.append(fields.pop())
                    else:
                        new_fields.append(v)
                fields = new_fields
            else:
                continue

            yield ShmecItem(
                province=province,
                school=school,
                major=fields[0],
                require=fields[1],
                remark=fields[2],
            )

def parse_linklist(text, remove_tags=False):
    data = []

    for row in text.split('\n'):
        rowparts = row.strip().split(' ')
        if len(rowparts) < 2:
            break
        time = rowparts[0]
        if rowparts[1].startswith('<') and rowparts[1].endswith('>'):
            url = rowparts[1][1:-1]
            textparts = rowparts[2:]
        else:
            url = ''
            textparts = rowparts[1:]
        text = ' '.join(textparts)
        if remove_tags:
            text = html.remove_tags(text)
        data.append(
            {
                'time': time,
                'url': url,
                'text': text
            }
        )
    return data

 def _extract_description(self, sel, item):
     return
     desc_xpath = '//div[@id="item-overview"]/ul/li/node()'
     data = sel.xpath(desc_xpath).extract()
     if len(data) != 0:
         data = [remove_tags(v.strip()) for v in data]
         description = ';'.join(data).replace(':;',':').replace('from;','from ')
         item['description'] = description

    def _extract_links(self, response_text, response_url, response_encoding):
        base_url = urljoin_rfc(response_url, self.base_url) if self.base_url else response_url

        clean_url = lambda u: urljoin_rfc(base_url, remove_entities(clean_link(u.decode(response_encoding))))
        clean_text = lambda t: replace_escape_chars(remove_tags(t.decode(response_encoding))).strip()

        links_text = linkre.findall(response_text)
        urlstext = set([(clean_url(url), clean_text(text)) for url, _, text in links_text])

        return [Link(url, text) for url, text in urlstext]

def clean_tags_from_affiliations(value):
    """Clean the affiliaton string for an author."""
    for affiliation in value.get('affiliations', []):
        # Remove tag AND content of any prefix like <label><sup>1</sup></label>
        affiliation['value'] = remove_tags_with_content(affiliation['value'], ('label',))
        # Now remove all tags but KEEP content
        affiliation['value'] = remove_tags(affiliation['value'])
        # Remove random whitespaces
        affiliation['value'] = clean_whitespace_characters(affiliation['value'])
    return value

    def process_response(self, request, response, spider):
        # clean body
        orig_body = response.body_as_unicode()
        body = remove_tags_with_content(orig_body, which_ones=('script', 'head'))
        body = remove_tags(remove_comments(body))
        terms = tokenize(body.lower())
        request.meta['terms'] = terms
        request.meta['body'] = body

        return response