Python element.Tag方法代码示例

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def parse_build_notes(h: Tag) -> None:
    entries = []
    for n in h.next_elements:
        if isinstance(n, Tag) and n.name == 'p':
            if 'posted-in' in n.attrs.get('class', []):
                break
            if n.text:
                entries.append(n.text)

    embed = {
        'title': 'MTGO Build Notes',
        'type': 'rich',
        'description': '\n'.join(entries),
        'url': fetcher.find_announcements()[0],
    }
    if configuration.get_optional_str('bugs_webhook_id') is not None:
        fetch_tools.post_discord_webhook(
            configuration.get_str('bugs_webhook_id'),
            configuration.get_str('bugs_webhook_token'),
            embeds=[embed],
            username='Magic Online Announcements',
            avatar_url='https://magic.wizards.com/sites/mtg/files/styles/auth_small/public/images/person/wizards_authorpic_larger.jpg'
            ) 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def parse_changelog(collapsible_block: Tag) -> None:
    # They never show Fixed bugs in the Bug Blog anymore.  Fixed bugs are now listed on the Build Notes section of MTGO weekly announcements.
    # This is frustrating.
    for added in collapsible_block.find_all('ul'):
        for item in added.find_all('li'):
            print(item)
            bbt = strings.remove_smartquotes(item.get_text())

            issue = find_issue_by_code(bbt)
            if issue is not None:
                if not repo.is_issue_from_bug_blog(issue):
                    print('Adding Bug Blog to labels')
                    issue.add_to_labels('From Bug Blog')
            elif find_issue_by_name(bbt):
                print('Already exists.')
            else:
                print('Creating new issue')
                text = 'From Bug Blog.\nBug Blog Text: {0}'.format(bbt)
                repo.get_repo().create_issue(bbt, body=strings.remove_smartquotes(text), labels=['From Bug Blog']) 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def check_if_removed_from_bugblog(bbt: Match, b: Tag, issue: Issue) -> None:
    if bbt is not None:
        text = strings.remove_smartquotes(bbt.group(1).strip())
        for row in b.find_all('tr'):
            data = row.find_all('td')
            rowtext = strings.remove_smartquotes(data[1].text.strip())
            if rowtext == text:
                break
            if strip_squarebrackets(rowtext) == strip_squarebrackets(text):
                # Fix this
                print("Issue #{id}'s bug blog text has differing autocard notation.".format(id=issue.number))
                old_bbt = strings.get_body_field(issue.body, 'Bug Blog Text')
                body = re.sub(BBT_REGEX, 'Bug Blog Text: {0}'.format(rowtext), issue.body, flags=re.MULTILINE)
                new_bbt = strings.get_body_field(body, 'Bug Blog Text')
                issue.edit(body=body)
                print('Updated to `{0}`'.format(rowtext))
                issue.create_comment(f'Changed bug blog text from `{old_bbt}` to `{new_bbt}`')
                break
        else:
            print('{id} is fixed!'.format(id=issue.number))
            repo.create_comment(issue, 'This bug has been removed from the bug blog!')
            issue.edit(state='closed') 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def get_tag_from_bs(cls, soup):
        from bs4 import BeautifulSoup as bs
        from bs4.element import Tag as bs_tag
        father = None
        if isinstance(soup, bs):
            father = soup.find()
        elif isinstance(soup, bs_tag):
            father = soup
        if not father or not father.name:
            return None

        tag = cls(father.name, father.text, father.attrs)

        for c in father.children:
            c_tag = cls.get_tag_from_bs(c)
            tag.append(c_tag)
        return tag 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def ensure_soup(value, parser=None):
    """Coerce a value (or list of values) to Tag (or list of Tag).

    :param value: String, BeautifulSoup, Tag, or list of the above
    :param str parser: Parser to use; defaults to BeautifulSoup default
    :return: Tag or list of Tags

    """
    if isinstance(value, BeautifulSoup):
        return value.find()
    if isinstance(value, Tag):
        return value
    if isinstance(value, list):
        return [
            ensure_soup(item, parser=parser)
            for item in value
        ]
    parsed = BeautifulSoup(value, features=parser)
    return parsed.find() 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def decrypt_woff_tag(tag,TTGlyphs,d_list):
    contents = tag.contents
    _ = []
    while contents:
        i = contents.pop(0)
        if isinstance(i, Tag):
            if i.name in decrypt_tags:
                text = dec(i.text)
                for index,name in enumerate(TTGlyphs):
                    if text in name:
                        i = d_list[index]
            else:
                continue
        if not isinstance(i, str):
            continue
        _.append(i)
    return ''.join(_) 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def _match_end_tag(tag: Tag) -> bool:
        """Matches `tag` if its class value is in `SEARCH_END_TAG_ATTRS` or the tag is table."""
        for attr in SEARCH_END_TAG_ATTRS:
            if attr in tag.get("class", ()):
                return True

        return tag.name == "table" 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def parse_article_item_extended(a: Tag) -> Tuple[Tag, str]:
    title = a.find_all('h3')[0]
    link = 'http://magic.wizards.com' + a.find_all('a')[0]['href']
    return (title, link) 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def get_article_archive() -> List[Tuple[Tag, str]]:
    try:
        html = fetch_tools.fetch('http://magic.wizards.com/en/articles/archive/184956')
    except fetch_tools.FetchException:
        html = fetch_tools.fetch('http://magic.wizards.com/en/articles/archive/')
    soup = BeautifulSoup(html, 'html.parser')
    return [parse_article_item_extended(a) for a in soup.find_all('div', class_='article-item-extended')] 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def parse_header(h: Tag) -> None:
    txt = h.text
    if txt.startswith('Downtime'):
        parse_downtimes(h)
    elif txt.startswith('Build Notes'):
        parse_build_notes(h) 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def parse_downtimes(h: Tag) -> None:
    for n in h.next_elements:
        if isinstance(n, Tag) and n.text:
            with open('downtimes.txt', 'w', encoding='utf-8') as f:
                txt = n.text.strip()
                txt = txt.replace("Please note that there are no more 'extended' or 'normal' downtimes; in the new world with fewer downtimes, they're all the same length of time.", '')
                print(txt)
                f.write(txt)
            break 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def check_for_missing_bugs(b: Tag) -> None:
    for row in b.find_all('tr'):
        data = row.find_all('td')
        row_text = data[1].text.strip()
        if row_text == 'Description':
            # BS4 is bad.
            continue
        issue = find_issue_by_code(row_text)
        if issue:
            labels = [c.name for c in issue.labels]
            categories = [c for c in labels if c in strings.METACATS]
            if categories:
                continue
            bbcat = re.match(strings.REGEX_BBCAT, data[2].text.strip())
            if bbcat is None:
                continue
            g1 = bbcat.group(1).strip()
            if g1 in strings.METACATS:
                issue.add_to_labels(g1)
                continue
            if bbcat.group(2) is not None:
                g2 = bbcat.group(2).strip()
                if g2 in strings.METACATS:
                    issue.add_to_labels(g2)
                    continue
            print(f'Unknown BBCat: {bbcat.group(0)}')
            continue
        print('Could not find issue for `{row}`'.format(row=row_text))
        text = 'From Bug Blog.\nBug Blog Text: {0}'.format(row_text)
        repo.get_repo().create_issue(strings.remove_smartquotes(row_text), body=strings.remove_smartquotes(text), labels=['From Bug Blog']) 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def find_bbt_in_issue_title(issue: Issue, known_issues: Tag) -> None:
    title = strip_squarebrackets(issue.title).replace(' ', '')
    for row in known_issues.find_all('tr'):
        data = row.find_all('td')
        row_text = strip_squarebrackets(data[1].text.strip()).replace(' ', '')
        if row_text == title:
            body = issue.body
            body += '\nBug Blog Text: {0}'.format(data[1].text.strip())
            if body != issue.body:
                issue.edit(body=body)
            return 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def _coordinates_from_HTML(
        self, page: Tag, page_num: int
    ) -> Tuple[
        List[PdfWord], Dict[PdfWordId, Bbox],
    ]:
        pdf_word_list: List[PdfWord] = []
        coordinate_map: Dict[PdfWordId, Bbox] = {}
        block_coordinates: Dict[PdfWordId, Tuple[int, int]] = {}
        blocks = page.find_all("block")
        i = 0  # counter for word_id in page_num
        for block in blocks:
            x_min_block = int(float(block.get("xmin")))
            y_min_block = int(float(block.get("ymin")))
            lines = block.find_all("line")
            for line in lines:
                y_min_line = int(float(line.get("ymin")))
                y_max_line = int(float(line.get("ymax")))
                words = line.find_all("word")
                for word in words:
                    xmin = int(float(word.get("xmin")))
                    xmax = int(float(word.get("xmax")))
                    for content in self.separators.split(word.getText()):
                        if len(content) > 0:  # Ignore empty characters
                            word_id: PdfWordId = (page_num, i)
                            pdf_word_list.append((word_id, content))
                            coordinate_map[word_id] = Bbox(
                                page_num, y_min_line, y_max_line, xmin, xmax,
                            )
                            block_coordinates[word_id] = (y_min_block, x_min_block)
                            i += 1
        # sort pdf_word_list by page, block top then block left, top, then left
        pdf_word_list = sorted(
            pdf_word_list,
            key=lambda word_id__: block_coordinates[word_id__[0]]
            + (coordinate_map[word_id__[0]].top, coordinate_map[word_id__[0]].left),
        )
        return pdf_word_list, coordinate_map 

# 需要导入模块: from bs4 import element [as 别名]
# 或者: from bs4.element import Tag [as 别名]
def lowercase_attr_names(tag):
    """Lower-case all attribute names of the provided BeautifulSoup tag.
    Note: this mutates the tag's attribute names and does not return a new
    tag.

    :param Tag: BeautifulSoup tag

    """
    # Use list comprehension instead of dict comprehension for 2.6 support
    tag.attrs = dict([
        (key.lower(), value)
        for key, value in iteritems(tag.attrs)
    ])