python - Beautiful Soup 迭代 html 标签

Question

我在 html 中有以下代码

<section>
    <section>
        <h2>Title1</h2>
        <p>Text1</p>
        <p>Text1</p>
     </section>
  <section>
        <h2>Title2</h2>
        <p>Text2</p>
        <p>Text2</p>
     </section>
  <section>
        <h2>Title3</h2>
        <p>Text3</p>
        <p>Text3</p>
     </section>
  </section>
<section>
        <h2>Title2-1</h2>
        <p>Text2-1</p>
        <p>Text2-1</p>
</section>
<section>
        <h2>Title3-1</h2>
        <p>Text3-1</p>
        <p>Text3-1</p>
</section>

因为有些部分有小节，有些则没有。 我想获取子部分和没有子部分的部分的内容 我正在尝试迭代这些小节，以便我可以在 scrapy 中创建索引。 我有以下 scrapy 代码:

class RUSpider(BaseSpider):
name = "ru"
allowed_domains = ["http://127.0.0.1:8000/"]
start_urls = [
    "http://127.0.0.1:8000/week2/1_am/#/",
    "http://127.0.0.1:8000/week1/1/",
    "http://127.0.0.1:8000/week3/1_am/"
]
rules = [
    Rule(SgmlLinkExtractor(), follow=True)
]

def parse(self, response):

    filename = response.url.split("/")[3]
    hxs = HtmlXPathSelector(response)
    divs = hxs.select('//div')
    sections = divs.select('//section').extract()
   # print sections.extract


 #class definition for scrapy and html selector

    for each in sections: #iterate over loop [above sections]
        soup = BeautifulSoup(each)
        sp= soup.prettify()
        elements = soup.findAll("section".split())
        print len(elements),'sublength'
        if len(elements ) > 1:
            for element in elements:
                for subelement in element:
                    print subelement,'element'
        else:
            item = RItem() # create Index Item
            item['html_content'] = each
            print each
            yield item

尽管某些没有小节的部分被分解为单独的元素，但某些结果的格式正确。

我想要单独的每个部分。我的意思是因为 1 个部分还有其他部分。我想循环这些部分并单独获取它们，以便我可以跟踪循环。由于某些部分没有子部分，因此无需循环遍历它们。

在 BeautifulSoup 中有更好的方法吗？ 我想要以下输出

    <section>
        <h2>Title1</h2>
        <p>Text1</p>
        <p>Text1</p>
     </section>
  <section>
        <h2>Title2</h2>
        <p>Text2</p>
        <p>Text2</p>
     </section>
  <section>
        <h2>Title3</h2>
        <p>Text3</p>
        <p>Text3</p>
     </section>
 
    <section>
            <h2>Title2-1</h2>
            <p>Text2-1</p>
            <p>Text2-1</p>
    </section>
    <section>
            <h2>Title3-1</h2>
            <p>Text3-1</p>
            <p>Text3-1</p>
    </section>

Answer 1

检查此方法。这是您提供的数据的通用数据。

data = """
<section>
    <section>
        <h2>Title1</h2>
        <p>Text1</p>
        <p>Text1</p>
     </section>
  <section>
        <h2>Title2</h2>
        <p>Text2</p>
        <p>Text2</p>
     </section>
  <section>
        <h2>Title3</h2>
        <p>Text3</p>
        <p>Text3</p>
     </section>
  </section>
<section>
        <h2>Title2-1</h2>
        <p>Text2-1</p>
        <p>Text2-1</p>
</section>
<section>
        <h2>Title3-1</h2>
        <p>Text3-1</p>
        <p>Text3-1</p>
</section>
"""
from bs4 import BeautifulSoup

soup = BeautifulSoup(data)

sections = soup.find_all('section')


for each in sections: #iterate over loop [above sections]
    if each.find('section'):
        continue
    else:
        print each.prettify()