Python PyQuery.find方法代码示例

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
    def test_calendar_tag_rendering(self, timezone_mock):
        timezone_mock.now.return_value = tz_datetime(2015, 1, 10, 12)
        page_with_apphook = self.create_base_pages()
        other_config = EventsConfig.objects.create(namespace='other')
        self.create_event(
            title='ev1',
            start_date=tz_datetime(2015, 1, 13),
            publish_at=tz_datetime(2015, 1, 10)
        )
        self.create_event(
            title='ev2',
            start_date=tz_datetime(2015, 1, 15),
            publish_at=tz_datetime(2015, 1, 10)
        )
        self.create_event(
            de=dict(
                title='ev3',
                start_date=tz_datetime(2015, 1, 16),
                publish_at=tz_datetime(2015, 1, 10)
            )
        )
        self.create_event(
            title='ev4',
            start_date=tz_datetime(2015, 1, 18),
            publish_at=tz_datetime(2015, 1, 10),
            app_config=other_config
        )
        self.create_event(
            title='ev5',
            start_date=tz_datetime(2015, 1, 22),
            end_date=tz_datetime(2015, 1, 27),
            publish_at=tz_datetime(2015, 1, 10)
        )
        self.create_event(
            title='ev6',
            start_date=tz_datetime(2015, 1, 25),
        )
        # make use of default tests self.app_config namespace, instead of
        # hard coding it
        template_str = """
        {%% load aldryn_events %%}
        {%% calendar 2015 1 'en' '%s' %%}
        """ % self.app_config.namespace
        t = Template(template_str)
        with override('en'):
            html = t.render(SekizaiContext({}))
            table = PyQuery(html)('table.table-calendar')
            page_url_en = page_with_apphook.get_absolute_url()
        links = table.find('td.events, td.multiday-events').find('a')

        # test if tag rendered important elements
        self.assertEqual('1', table.attr('data-month-numeric'), )
        self.assertEqual('2015', table.attr('data-year'))
        self.assertEqual('10', table.find('td.today').text())
        self.assertEqual(8, links.length)  # 13, 15, 22, 23, 24, 25, 26, 27
        expected_days = (13, 15, 22, 23, 24, 25, 26, 27)
        for position, day in enumerate(expected_days):
            event_url = '{0}2015/1/{1}/'.format(page_url_en, day)
            rendered_url = links[position].attrib['href']
            self.assertEqual(event_url, rendered_url)

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
def get_old_fashion_comments(answer_url):
  aid = comment_list_id(answer_url)
  comment_box_link = 'http://www.zhihu.com/node/AnswerCommentBoxV2?params=%7B%22answer_id%22%3A%22{}%22%2C%22load_all%22%3Atrue%7D'.format(aid)  # | log
  # log('comments: ' + comment_box_link)
  r = old_client._session.get(comment_box_link)
  # print(str(r.content))
  doc = PyQuery(str(r.content, encoding='utf-8'))
  comments = []
  for div in doc.find('div.zm-item-comment'):
    div = PyQuery(div)
    cid = div.attr('data-id')
    vote_count = int(div.find('span.like-num').find('em').text())
    content = div.find('div.zm-comment-content').html()
    author_text = div.find('div.zm-comment-hd').text().replace('\n', ' ')
    if ' 回复 ' in author_text:
      author, reply_to = author_text.split(' 回复 ')
    else:
      author, reply_to = author_text, None

    comment = OldFashionComment(cid=cid,
                                vote_count=vote_count,
                                content=content,
                                author=OldFashionAuthor(author),
                                reply_to=OldFashionAuthor(reply_to) if reply_to else None)
    comments.append(comment)
  return comments

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
    def update_forums(client, group, session):
        logging.info("Updating forums list for {}".format(group))
        query = Forum.get_forum_page(client, group.gid)
        reg = regex.compile(r"^forum\.php\?mod=forumdisplay&fid=(\d+)$")

        for row in query.find("table.fl_tb>tr"):
            sub_query = PyQuery(row)
            href = sub_query.find("td").eq(1).find("a").attr("href")
            if not href:
                continue

            fid = int(reg.findall(href)[0])

            name = sub_query.find("td").eq(1).find("h2>a").clone().children().remove().end().text()
            last_update = sub_query.find("td").eq(3).find("div>cite").clone().children().remove().end().text()
            last_update = dateparse(last_update)

            existence = session.query(Forum).filter(Forum.fid == fid)
            if existence.count() == 0:
                logging.info("<Forum(fid={})> not found, creating one".format(fid))
                forum = Forum(fid=fid, name=name, updated_at=last_update, group=group, fresh=False)
                session.add(forum)
            else:
                forum = existence.one()
                if forum.updated_at != last_update:
                    logging.info("{} found, stale: against {} ".format(forum, last_update))
                    forum.updated_at = last_update
                    forum.fresh = False
                    session.add(forum)
                else:
                    logging.info("{} found, fresh".format(forum))

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
def get_phonetic_symbol(text):
    data = { "keyfrom" : "deskdict.mini", "q" : text, "doctype" : "xml", "xmlVersion" : 8.2,
             "client" : "deskdict", "id" : "cee84504d9984f1b2", "vendor": "unknown", 
             "in" : "YoudaoDict", "appVer" : "5.4.46.5554", "appZengqiang" : 0, "le" : "eng", "LTH" : 40}
    ret = requests.get("http://dict.youdao.com/search", params=data).text
    if isinstance(ret, unicode):
        ret = ret.encode('utf-8')
    pq = PyQuery(ret, parser="xml")
    
    phonetic_symbol = pq.find('usphone').text()
    phonetic_type = _("US")
    
    try:    
        if phonetic_symbol == '':
            phonetic_symbol = pq.find('ukphone').text()
            phonetic_type = _("UK")
    except: 
        pass
    
    if phonetic_symbol == '' or phonetic_symbol == None or phonetic_symbol.isspace():
        return ""
    else:
        if isinstance(phonetic_type, unicode):
            phonetic_type = phonetic_type.encode('utf-8')

        if isinstance(phonetic_symbol, unicode):
            phonetic_symbol = phonetic_symbol.encode('utf-8')
        
        return "[%s] %s" % (phonetic_type, phonetic_symbol)

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
    def _parse_table(self, table):

        # Initialize table
        parsed_rows = []

        # Parse table
        qtable = PyQuery(table)

        # Get headers
        headers = self._get_headers(qtable)
        if not headers:
            return

        # Get rows
        rows = qtable.find("tr")

        # Loop over rows
        for row in rows:

            # Get columns
            qrow = PyQuery(row)
            cols = qrow.find("td").map(self._get_text)[:]

            # Parse column values
            for colidx in range(len(cols)):
                col = reduce(lambda x, y: re.sub(y[0], y[1], x), self._trans, cols[colidx])
                cols[colidx] = col

            # Append parsed columns
            if cols:
                parsed_rows.append(cols)

        return {"headers": headers, "data": parsed_rows}

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
def get_url(url):
    response = requests.get(url)
    doc = PyQuery(response.text)
    for article in doc('article'):
        h = PyQuery(article)
        print h.find('h1.entry-title').text().encode('utf-8')
        print h.find('div.entry-content p').text().encode('utf-8')

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
def process_chapter(chapter_path, index_path, enable_stem) :

	# removed characters
	remove_chars = ['.',',',';','?','!','-',u'–',u'―',u'—',u'~',':','"',')','(','[',']','/','\\',"'s",u'’s',"'",u'‘',u'’',u'“',u'”', u'¿', '*', '<','>','&','{','}']

	restricted_words = ['a', 'and', 'about', 'above', 'across', 'after', 'against', 'along', 'among', 'around', 'at', 'before', 'behind', 'below', 'beneath', 'beside', 'between', 'beyond', 'but', 'by', 'despite', 'down', 'during', 'except', 'for', 'from', 'in', 'inside', 'into', 'like', 'near', 'of', 'off', 'on', 'onto', 'out', 'outside', 'over', 'past', 'since', 'the', 'through', 'throughout', 'till', 'to', 'toward', 'under', 'underneath', 'until', 'up', 'upon', 'with', 'within', 'without']
		
	# create jQuery object
	html = open(chapter_path, 'r').read()
	jquery = PyQuery(html)
	
	print jquery.find('.chapter').attr('data-osis')
	
	# find all verses, remove all notes and verse numbers
	verses = jquery('span.verse')
	verses.find('span.note').remove()
	verses.find('span.cf').remove()
	verses.find('.v-num').remove()
	
	for verse in verses:
		v = PyQuery(verse)
		osis = v.attr('data-osis')
		text = v.text()
		
		# remove punctuation
		for s in remove_chars:
			text = text.replace(s, '')
		
		words = text.split(' ')
		
		for word in words:
			word = word.strip().lower()
			
			#there's got to be a cleaner way to do this in Python
			is_restricted = True
			try:
				restricted_words.index(word)
			except:	
				is_restricted = False
								
			if word != '' and not is_restricted and not word.isnumeric():
			
				# stemmer?
				if enable_stem:
					word = stem(word)
			
				word_path = index_path + word + '.json'
				
				# check for file
				if os.path.exists(word_path):
					f = open(word_path,'a')
					f.write(',"' + osis + '"')
					f.close()
				else:
					f = open(word_path,'a')
					f.write('["' + osis + '"')
					f.close()				

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
    def getFullInfo(self, interval=0.5):
        self.getBasicInfo()

        # collCount
        if self.INFO['shopType'] in ['7', '1', '3', '4']:
            regxrs = re.findall(
                r'J_SCollCount\"\s+data\-info\=\"param\=(.+?)\&',
                self.content)
            if regxrs:
                params = {'keys': regxrs[0], 't': '%.0f' % (time.time()
                          * 1000), 'callback': 'TShop.setShopStat'}
                domain = 'http://count.tbcdn.cn/counter3'
                tUrl = domain + '?' + '&'.join([k + '=' + v for (k, v) in
                                                params.items()])
                r = request(tUrl)
                self.INFO['collCount'] = str(re.findall(r'\"\S+\"\:(\d+)',
                                                        r.text, re.S)[0])
            else:
                if PyQuery:
                    pyjq_obj = PyQuery(self.content.decode(self.res.encoding))
                    data_info = (pyjq_obj.find('dl.collect-num dt') or pyjq_obj.find('.collect-num span')).attr('data-info')
                    count_url = re.sub(
                        r'param=(?P<param>.+?)\&countUrl=(?P<count>.+?)\&.+',
                        r'\g<count>?callback=jsonp357&t=%d&keys=\g<param>' % (time.time()*1000),
                        data_info,
                        re.S)
                    collCount = re.sub(
                        r'.+\:\s*(?P<coll>\d+).+',
                        r'\g<coll>',
                        request(count_url).content)
                    if collCount:
                        self.INFO['collCount'] = int(collCount)

        else:
            coll_url = 'http://favorite.taobao.com/collect_item_relation.htm?itemtype=0&itemNumid=%s' % self.INFO['shopId']
            try:
                res = request(coll_url)
                pyjq_obj = PyQuery(res.content.decode(res.encoding))
                self.INFO['collCount'] = pyjq_obj.find("div.add-fav-msg strong").html().strip()
            except:
                pass
        time.sleep(interval)

        # itemAmount
        if self.INFO['shopType'] == '2':
            tUrl = self.INFO['shopLink'] + '?search=y&orderType=_hotsell'
            r = request(tUrl)
            try:
                self.INFO['itemAmount'] = \
                    str(re.findall(r'\<div\s+class\=\"search\-result\"\s*\>.+?(\d+)', r.text, re.S)[0])
            except:
                pass
        time.sleep(interval)
        return self.INFO

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
    def test_device_elements(self):
        response = self.client.get(self.url)
        self.assertEqual(response.status_code, 200)

        tree = PyQuery(response.content)
        radios = tree.find('input[type="radio"]')
        self.assertEqual(len(radios), 2)

        tree = PyQuery(response.content)
        checkboxes = tree.find('input[type="checkbox"]')
        self.assertEqual(len(checkboxes), 1)

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
    def test_initial_post(self):
        mock_request = self._get_post_request(type='generic')
        response, MockDevice = self._post_device_addition(mock_request)

        self.assertEqual(response.status_code, 200)
        self.assertFalse(MockDevice.objects.create.called)

        tree = PyQuery(response.content)
        self.assertEqual(len(tree.find('.error')), 0)
        device_name = tree.find('input[type=text][name=name]')
        self.assertEqual(len(device_name), 1)
        self.assertEqual(device_name.val(), 'Authentication device')

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
    def parse(self, response):
        html = Pq(response.body)
        job = items.OnetJob()
        job['url'] = response.url
        job['alt_title'] = html.find('[class="titleb"]').text()
        job['job_sample'] = html.find(
            'p:contains("Sample of reported job titles:")').text()

        job['summary'] = html.find(
            '#realcontent').find('p:eq(0)').text()

        job['job_sample'] = job['job_sample'].replace(
            'Sample of reported job titles:', '').split(', ')

        job['tasks'] = self._list(html, '.section_Tasks .moreinfo')
        job['tools'] = self._list(
            html, '.section_ToolsTechnology .moreinfo:first')
        job['technology'] = self._list(
            html, '.section_ToolsTechnology .moreinfo:last')
        job['knowledge'] = self._list(html, '.section_Knowledge .moreinfo')
        job['skills'] = self._list(html, '.section_Skills .moreinfo')
        job['abilities'] = self._list(html, '.section_Abilities .moreinfo')
        job['work_activities'] = {
            'basic': self._list(html, '.section_WorkActivities .moreinfo'),
            'detailed': self._list(
                html, '.section_DetailedWorkActivities .moreinfo'),
        }
        job['work_context'] = self._list(
            html, '.section_WorkContext .moreinfo')

        job['job_zone'] = self._table(html, '#content table:first')
        job['education'] = self._table(html, '#content table:eq(1)')

        job['interests'] = self._list(html, None, custom=html.find(
            '[name="Interests"]').siblings('.moreinfo:first'))

        job['work_styles'] = self._list(
            html, '.section_WorkStyles .moreinfo')

        job['interests'] = self._list(html, None, custom=html.find(
            '[name="WorkValues"]').siblings('.moreinfo:eq(1)'))

        job['related_occupations'] = self._table(
            html, '.section_RelatedOccupations table')

        job['wages_employment'] = self._table(
            html, '[summary="Wages & Employment Trends information'
                  ' for this occupation"]')

        job['job_openings'] = ''
        job['additional_info'] = ''
        return job

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
def _fetch_mdn_page(url):
    data = bleach.clean(_get_page(url), attributes=ALLOWED_ATTRIBUTES,
                        tags=ALLOWED_TAGS, strip_comments=False)

    root = PyQuery(data)
    toc = root.find('#article-nav div.page-toc ol')[0]
    content = root.find('#pageText')[0]

    toc.set('id', 'mdn-toc')
    content.set('id', 'mdn-content')

    return (etree.tostring(toc, pretty_print=True),
        etree.tostring(content, pretty_print=True))

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
 def parse(self, response):
     category = items.ONetCategory()
     html = Pq(response.body)
     category['url'] = response.url
     category['name'] = html.find('.reportdesc:eq(0)').text().replace(
         'Save Table ( XLS / CSV )', '')
     category['id'] = response.url.replace('{}?i'.format(
         self.root_url), '').replace(
             '&g=Go', '').replace('=', '').replace('.', '')
     category['bls_url'] = html.find(
         'div.reportdesc a:first').attr('href')
     category['occupation_data'] = self._extract_occupations(html)
     return category

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
 def feed(self, data, sentence):
     d = PyQuery(data)
     sets = d(".sentences_set")
     for s in sets:
         s = PyQuery(s)
         if s.find(".mainSentence .sentenceContent a").text().strip() == sentence:
             structure = s.find(".mainSentence .sentenceContent .romanization.furigana").text()
             translations = s.find(".translations:first") \
                             .find(".sentence > img[title='English']") \
                             .parent().find(".sentenceContent > a") \
                             .map(lambda i, o: o.text)
             return (structure, translations)
     return (None, None)

# 需要导入模块: from pyquery import PyQuery [as 别名]
# 或者: from pyquery.PyQuery import find [as 别名]
def get_meme_url(meme):
    gen = GENERATORS.get(meme)
    if gen:
        pq = PyQuery(url="http://memegenerator.net/%s" % gen[2])
        return pq.find('a img.large').attr('src')
    else:
        return None