python - Beautifulsoup 如何重新组合单词

import requests, codecs from bs4 import BeautifulSoup from bs4.element import Comment path='C:\\Users\\jason\\Google Drive\\python\\' def tag_visible(element): if element.parent.name in ['sup']: return False if isinstance(element, Comment): return False return True ticker = 'TSLA' quarter = '18Q2' mark1= 'ITEM 1A' mark2= 'UNREGISTERED SALES' url_new='https://www.sec.gov/Archives/edgar/data/1318605/000156459018019254/tsla-10q_20180630.htm' def get_text(url,mark1,mark2): html = requests.get(url) soup = BeautifulSoup(html.text, 'html.parser') for hr in soup.select('hr'): hr.find_previous('p').extract() texts = soup.findAll(text=True) visible_texts = filter(tag_visible, texts) text=u" ".join(t.strip() for t in visible_texts) return text[text.find(mark1): text.find(mark2)] text = get_text(url_new,mark1,mark2) file=codecs.open(path + "test.txt", 'w', encoding='utf8') file.write (text) file.close()

您正在处理使用 Microsoft Word 格式化的 HTML。不要提取文本并尝试在没有该上下文的情况下对其进行处理。

您要处理的部分用<a name="...">标签清楚地描绘出来，让我们从选择所有带有<a name="ITEM_1A_RISK_FACTORS">标记的元素开始，一直到但不包括<a name="ITEM2_UNREGISTERED_SALES">标记：

def sec_section(soup, item_name):
    """iterate over SEC document paragraphs for the section named item_name

    Item name must be a link target, starting with ITEM
    """

    # ask BS4 to find the section
    elem = soup.select_one('a[name={}]'.format(item_name))
    # scan up to the parent text element
    # html.parser does not support <text> but lxml does
    while elem.parent is not soup and elem.parent.name != 'text':
        elem = elem.parent

    yield elem
    # now we can yield all next siblings until we find one that
    # is also contains a[name^=ITEM] element:
    for elem in elem.next_siblings:
        if not isinstance(elem, str) and elem.select_one('a[name^=ITEM]'):
            return
        yield elem

该函数为我们提供<text>了 HTML 文档中从包含特定链接目标的段落开始的节点的所有子节点，一直到名为ITEM.

接下来，通常的Word清理任务是去除标签、style属性：

def clean_word(elem):
    if isinstance(elem, str):
        return elem
    # remove last-rendered break markers, non-rendering but messy
    for lastbrk in elem.select('a[name^=_AEIOULastRenderedPageBreakAEIOU]'):
        lastbrk.decompose()
    # remove font tags and styling from the document, leaving only the contents
    if 'style' in elem.attrs:
        del elem.attrs['style']
    for e in elem:  # recursively do the same for all child nodes
        clean_word(e)
    if elem.name == 'font':
        elem = elem.unwrap()
    return elem

该Tag.unwrap()方法对您的情况最有帮助，因为文本几乎被标签任意划分。

现在，干净地提取文本突然变得微不足道了：

for elem in sec_section(soup, 'ITEM_1A_RISK_FACTORS'):
    clean_word(elem)
    if not isinstance(elem, str):
        elem = elem.get_text(strip=True)
    print(elem)

在文本的其余部分中，这会输出：

•that the equipment and processes which we have selected for Model 3 production will be able to accurately manufacture high volumes of Model 3 vehicles within specified design tolerances and with high quality;

文本现在已正确连接，不再需要重新组合。

整个部分仍在表格中，但clean_word()现在将其清理为更合理的：

<div align="left">
<table border="0" cellpadding="0" cellspacing="0">
<tr>
<td valign="top">
<p> </p></td>
<td valign="top">
<p>•&lt;/p></td>
<td valign="top">
<p>that the equipment and processes which we have selected for Model 3 production will be able to accurately manufacture high volumes of Model 3 vehicles within specified design tolerances and with high quality;</p></td></tr></table></div>

因此您可以使用更智能的文本提取技术来进一步确保此处的文本转换干净；您可以将此类项目符号表转换为*前缀，例如：

def convert_word_bullets(soup, text_bullet="*"):
    for table in soup.select('div[align=left] > table'):
        div = table.parent
        bullet = div.find(string='\u2022')
        if bullet is None:
            # not a bullet table, skip
            continue
        text_cell = bullet.find_next('td')
        div.clear()
        div.append(text_bullet + ' ')
        for i, elem in enumerate(text_cell.contents[:]):
            if i == 0 and elem == '\n':
                continue  # no need to include the first linebreak
            div.append(elem.extract())

此外，如果您运行，您可能也想跳过分页符（[page number]和<hr/>元素的组合）

for pagebrk in soup.select('p ~ hr[style^=page-break-after]'): 
    pagebrk.find_previous_sibling('p').decompose()
    pagebrk.decompose()

这比您自己的版本更明确，您可以删除所有<hr/>元素和前面的元素，无论它们是否实际上是同级元素。

在清理 Word HTML之前执行这两项操作。结合你的功能，一起变成：

def get_text(url, item_name):
    response = requests.get(url) 
    soup = BeautifulSoup(response.content, 'html.parser')

    for pagebrk in soup.select('p ~ hr[style^=page-break-after]'): 
        pagebrk.find_previous_sibling('p').decompose()
        pagebrk.decompose()

    convert_word_bullets(soup)
    cleaned_section = map(clean_word, sec_section(soup, item_name))

    return ''.join([
        elem.get_text(strip=True) if elem.name else elem
        for elem in cleaned_section])


text = get_text(url, 'ITEM_1A_RISK_FACTORS')
with open(os.path.join(path, 'test.txt'), 'w', encoding='utf8') as f:
    f.write(text)

python - Beautifulsoup 如何重新组合单词

问题描述

解决方案

推荐阅读