def clean_em_tags(doc): ems = parser.get_elements_by_tag(doc, tag='em') for node in ems: images = parser.get_elements_by_tag(node, tag='img') if len(images) == 0: node.drop_tag() return doc
def is_table_tag_and_no_paragraphs_exist(e): sub_paragraphs = parser.get_elements_by_tag(e, tag='p') for p in sub_paragraphs: txt = parser.get_text(p) if len(txt) < 25: parser.remove(p) sub_paragraphs2 = parser.get_elements_by_tag(e, tag='p') if len(sub_paragraphs2) == 0 and e.tag is not "td": return True return False
def remove_script_and_style(doc): # remove scripts scripts = parser.get_elements_by_tag(doc, tag='script') for item in scripts: parser.remove(item) # remove styles styles = parser.get_elements_by_tag(doc, tag='style') for item in styles: parser.remove(item) # remove comments comments = parser.get_comments(doc) for item in comments: parser.remove(item) return doc
def sibling_content(current_sibling, sibling_paragraphs_baseline_score): """ Adds any siblings that may have a decent score to this node """ if current_sibling.tag == 'p' \ and len(parser.get_text(current_sibling)) > 0: e0 = current_sibling if e0.tail: e0 = copy.deepcopy(e0) e0.tail = '' return [e0] else: potential_paragraphs = parser.get_elements_by_tag(current_sibling, tag='p') if potential_paragraphs is None: return None else: ps = [] for first_paragraph in potential_paragraphs: text = parser.get_text(first_paragraph) if len(text) > 0: word_stats = StopWords().get_stop_word_count(text) paragraph_score = word_stats.get_stop_word_count() sibling_baseline_score = float(.30) high_link_density = is_high_link_density(first_paragraph) score = float(sibling_paragraphs_baseline_score * sibling_baseline_score) if score < paragraph_score and not high_link_density: p = parser.create_element(tag='p', text=text, tail=None) ps.append(p) return ps
def title(doc): """Return the document's title.""" title = '' title_elem = parser.get_elements_by_tag(doc, tag='title') # no title found if title_elem is None or len(title_elem) == 0: return title # title elem found title_text = parser.get_text(title_elem[0]) used_delimeter = False # split title with | if '|' in title_text: title_text = _split_title(title_text, "\\|") used_delimeter = True # split title with - if not used_delimeter and '-' in title_text: title_text = _split_title(title_text, " - ") used_delimeter = True # split title with » if not used_delimeter and u'»' in title_text: title_text = _split_title(title_text, "»") used_delimeter = True # split title with : if not used_delimeter and ':' in title_text: title_text = _split_title(title_text, ":") used_delimeter = True title = title_text.replace("�", "") return title
def meta_favicon(doc): """Return the document's meta favicon.""" kwargs = {'tag': 'link', 'attr': ' rel', 'value': 'icon'} meta = parser.get_elements_by_tag(doc, **kwargs) if meta: favicon = meta[0].attrib.get('href') return favicon return ''
def nodes_to_check(doc): """ Returns a list of nodes we want to search on like paragraphs and tables. """ nodes_to_check = [] for tag in ['p', 'pre', 'td']: items = parser.get_elements_by_tag(doc, tag=tag) nodes_to_check += items return nodes_to_check
def canonical_link(doc): """Return document's canonical link.""" kwargs = {'tag': 'link', 'attr': 'rel', 'value': 'canonical'} meta = parser.get_elements_by_tag(doc, **kwargs) if meta is not None and len(meta) > 0: href = meta[0].attrib.get('href') if href: href = href.strip() return href return ''
def remove_paragraphs_with_few_words(top_node): """ Remove paragraphs that have less than x number of words, would indicate that it's some sort of link. """ all_nodes = parser.get_elements_by_tags(top_node, ['*']) all_nodes.reverse() for el in all_nodes: text = parser.get_text(el) stop_words = StopWords().get_stop_word_count(text) if stop_words.get_stop_word_count() < 3 \ and len(parser.get_elements_by_tag(el, tag='object')) == 0 \ and len(parser.get_elements_by_tag(el, tag='embed')) == 0: parser.remove(el) # TODO: Check if it is in the right place. else: trimmed = parser.get_text(el) if trimmed.startswith("(") and trimmed.endswith(")"): parser.remove(el)
def meta_lang(doc): """Extract content language from meta.""" # we have a lang attribute in html attr = parser.get_attribute(doc, attr='lang') if attr is None: # look up for a Content-Language in meta kwargs = {'tag': 'meta', 'attr': ' http-equiv', 'value': 'content-language'} meta = parser.get_elements_by_tag(doc, **kwargs) if meta: attr = parser.get_attribute(meta[0], attr='content') if attr: value = attr[:2] if re.search('^[A-Za-z]{2}$', value): return value.lower() return None
def convert_div_to_p(doc, dom_type): bad_divs = 0 else_divs = 0 divs = parser.get_elements_by_tag(doc, tag=dom_type) tags = ['a', 'blockquote', 'dl', 'div', 'img', 'ol', 'p', 'pre', 'table', 'ul'] for div in divs: items = parser.get_elements_by_tags(div, tags) if div is not None and len(items) == 0: replace_elements_with_p(doc, div) bad_divs += 1 elif div is not None: replace_nodes = get_replacement_nodes(doc, div) div.clear() for c, n in enumerate(replace_nodes): div.insert(c, n) else_divs += 1 return doc
def is_high_link_density(e): """ Checks the density of links within a node, is there not much text and most of it contains linky shit? if so it's no good. """ links = parser.get_elements_by_tag(e, tag='a') if links is None or len(links) == 0: return False text = parser.get_text(e) words = text.split(' ') number_of_words = float(len(words)) sb = [] for link in links: sb.append(parser.get_text(link)) link_text = ''.join(sb) link_words = link_text.split(' ') number_of_link_words = float(len(link_words)) number_of_links = float(len(links)) link_divisor = float(number_of_link_words / number_of_words) score = float(link_divisor * number_of_links) if score >= 1.0: return True return False
def siblings_baseline_score(top_node): """ We could have long articles that have tons of paragraphs so if we tried to calculate the base score against the total text score of those paragraphs it would be unfair. So we need to normalize the score based on the average scoring of the paragraphs within the top node. For example if our total score of 10 paragraphs was 1000 but each had an average value of 100 then 100 should be our base. """ base = 100000 number_of_paragraphs = 0 score_of_paragraphs = 0 nodes_to_check = parser.get_elements_by_tag(top_node, tag='p') for node in nodes_to_check: node_text = parser.get_text(node) word_stats = StopWords().get_stop_word_count(node_text) high_link_density = is_high_link_density(node) if word_stats.get_stop_word_count() > 2 and not high_link_density: number_of_paragraphs += 1 score_of_paragraphs += word_stats.get_stop_word_count() if number_of_paragraphs > 0: base = score_of_paragraphs / number_of_paragraphs return base