Python 使用bs4在元素内单独取出元素

网站数据结构如下：

瓦片

->a

->div

def grabData(url):

    from urllib.request import urlopen as uReq
    from bs4 import BeautifulSoup as soup
    import pandas as pd
    import numpy as np


    my_url = url

    #opening up the connection, grabbing the page
    uClient = uReq(my_url)
    page_html = uClient.read()
    uClient.close()

    #html parsing
    page_soup = soup(page_html, "html.parser")

    #grabs each item
    tiles = page_soup.findAll('div', {'class':'category-tile-grid-item'})

    for tile in tiles:
        content_container = tile.findAll('div',{'class':'shop-tile__content--border-bottom'})
        store_name = content_container[0].text
        print(store_name)

if __name__ == '__main__':
    grabData('https://exchange.shopify.com/shops?sale_price=1000&shopify_shop_created_at=6m%2C0m')

->div

def grabData(url):

    from urllib.request import urlopen as uReq
    from bs4 import BeautifulSoup as soup
    import pandas as pd
    import numpy as np


    my_url = url

    #opening up the connection, grabbing the page
    uClient = uReq(my_url)
    page_html = uClient.read()
    uClient.close()

    #html parsing
    page_soup = soup(page_html, "html.parser")

    #grabs each item
    tiles = page_soup.findAll('div', {'class':'category-tile-grid-item'})

    for tile in tiles:
        content_container = tile.findAll('div',{'class':'shop-tile__content--border-bottom'})
        store_name = content_container[0].text
        print(store_name)

if __name__ == '__main__':
    grabData('https://exchange.shopify.com/shops?sale_price=1000&shopify_shop_created_at=6m%2C0m')

--->内容

------>p

------>p

------>p

->div

def grabData(url):

    from urllib.request import urlopen as uReq
    from bs4 import BeautifulSoup as soup
    import pandas as pd
    import numpy as np


    my_url = url

    #opening up the connection, grabbing the page
    uClient = uReq(my_url)
    page_html = uClient.read()
    uClient.close()

    #html parsing
    page_soup = soup(page_html, "html.parser")

    #grabs each item
    tiles = page_soup.findAll('div', {'class':'category-tile-grid-item'})

    for tile in tiles:
        content_container = tile.findAll('div',{'class':'shop-tile__content--border-bottom'})
        store_name = content_container[0].text
        print(store_name)

if __name__ == '__main__':
    grabData('https://exchange.shopify.com/shops?sale_price=1000&shopify_shop_created_at=6m%2C0m')

->div

def grabData(url):

    from urllib.request import urlopen as uReq
    from bs4 import BeautifulSoup as soup
    import pandas as pd
    import numpy as np


    my_url = url

    #opening up the connection, grabbing the page
    uClient = uReq(my_url)
    page_html = uClient.read()
    uClient.close()

    #html parsing
    page_soup = soup(page_html, "html.parser")

    #grabs each item
    tiles = page_soup.findAll('div', {'class':'category-tile-grid-item'})

    for tile in tiles:
        content_container = tile.findAll('div',{'class':'shop-tile__content--border-bottom'})
        store_name = content_container[0].text
        print(store_name)

if __name__ == '__main__':
    grabData('https://exchange.shopify.com/shops?sale_price=1000&shopify_shop_created_at=6m%2C0m')

我希望分别检索段落值。我该怎么做呢

编辑：

我已经按照orhan solak更新了我的代码

我现在想弄清楚如何在metrics容器中获得收入和其他价值。我该怎么做呢？为什么选择流量而不是收入？

我建议您使用特定的Xpath提取数据。我检查了您的代码，Xpath有点错误。我已经重新配置了你的代码。我把类名赋给了一个变量。之后，我将它们结合起来创建了一个精确的xpath。在下面的代码示例中；我创建了7个列表，分别包含价格、名称、网站类型、收入、流量、利润和库存价值

输出：

24
24
24
24
24
24
24

['$1,150USD', '$3,000USD', '$2,500USD', '$1,000USD', '$2,300USD']
['www.cosmicdetail.co.uk', 'prestige-timepiece.com', 'gomommyboutique.com', 'sunnysx.com', 'squishywishy.com']
['Automotive', 'Fashion and apparel', 'Toys and games', 'Fashion and apparel', 'Gifts and collectibles']
['$56', '$961', '$70', '$1.3K', '$403']
['111', '7.5K', '454', '2.8K', '2.6K']
['$50', '$1.0K', '$700', '$500', '$100']
['$1.8K', '', '', '', '']

"normalize-space(//div[@class='grid grid--equal-height']//div[@class='grid__item grid__item--tablet-up-third grid__item--desktop-up-quarter grid__item--wide-up-quarter gutter-bottom category-tile-grid-item layout-flex'][24]//div[@class='shop-tile__content shop-tile__metrics-container']//div[@class='shop-tile__metric'][1]//span[@class='shop-tile__metric__value text-bold'][1])"

DIODE BRAND
diodebrand.us
Art and photography

Private listing #572131
URL Hidden
Gifts and collectibles

检查清单：

print(price_list[:5])
print(name_list[:5])
print(website_type_list[:5])
print(revenue_list[:5])
print(traffic_list[:5])
print(profit_list[:5])
print(inventory_value_list[:5])

输出：

24
24
24
24
24
24
24

['$1,150USD', '$3,000USD', '$2,500USD', '$1,000USD', '$2,300USD']
['www.cosmicdetail.co.uk', 'prestige-timepiece.com', 'gomommyboutique.com', 'sunnysx.com', 'squishywishy.com']
['Automotive', 'Fashion and apparel', 'Toys and games', 'Fashion and apparel', 'Gifts and collectibles']
['$56', '$961', '$70', '$1.3K', '$403']
['111', '7.5K', '454', '2.8K', '2.6K']
['$50', '$1.0K', '$700', '$500', '$100']
['$1.8K', '', '', '', '']

"normalize-space(//div[@class='grid grid--equal-height']//div[@class='grid__item grid__item--tablet-up-third grid__item--desktop-up-quarter grid__item--wide-up-quarter gutter-bottom category-tile-grid-item layout-flex'][24]//div[@class='shop-tile__content shop-tile__metrics-container']//div[@class='shop-tile__metric'][1]//span[@class='shop-tile__metric__value text-bold'][1])"

DIODE BRAND
diodebrand.us
Art and photography

Private listing #572131
URL Hidden
Gifts and collectibles

如果要在控制台上尝试，请检查revenue的xpath：

revenue_xpath

输出：

24
24
24
24
24
24
24

['$1,150USD', '$3,000USD', '$2,500USD', '$1,000USD', '$2,300USD']
['www.cosmicdetail.co.uk', 'prestige-timepiece.com', 'gomommyboutique.com', 'sunnysx.com', 'squishywishy.com']
['Automotive', 'Fashion and apparel', 'Toys and games', 'Fashion and apparel', 'Gifts and collectibles']
['$56', '$961', '$70', '$1.3K', '$403']
['111', '7.5K', '454', '2.8K', '2.6K']
['$50', '$1.0K', '$700', '$500', '$100']
['$1.8K', '', '', '', '']

"normalize-space(//div[@class='grid grid--equal-height']//div[@class='grid__item grid__item--tablet-up-third grid__item--desktop-up-quarter grid__item--wide-up-quarter gutter-bottom category-tile-grid-item layout-flex'][24]//div[@class='shop-tile__content shop-tile__metrics-container']//div[@class='shop-tile__metric'][1]//span[@class='shop-tile__metric__value text-bold'][1])"

DIODE BRAND
diodebrand.us
Art and photography

Private listing #572131
URL Hidden
Gifts and collectibles

我建议您使用特定的Xpath来提取数据。我检查了您的代码，Xpath有点错误。我已经重新配置了你的代码。我把类名赋给了一个变量。之后，我将它们结合起来创建了一个精确的xpath。在下面的代码示例中；我创建了7个列表，分别包含价格、名称、网站类型、收入、流量、利润和库存价值

输出：

24
24
24
24
24
24
24

['$1,150USD', '$3,000USD', '$2,500USD', '$1,000USD', '$2,300USD']
['www.cosmicdetail.co.uk', 'prestige-timepiece.com', 'gomommyboutique.com', 'sunnysx.com', 'squishywishy.com']
['Automotive', 'Fashion and apparel', 'Toys and games', 'Fashion and apparel', 'Gifts and collectibles']
['$56', '$961', '$70', '$1.3K', '$403']
['111', '7.5K', '454', '2.8K', '2.6K']
['$50', '$1.0K', '$700', '$500', '$100']
['$1.8K', '', '', '', '']

"normalize-space(//div[@class='grid grid--equal-height']//div[@class='grid__item grid__item--tablet-up-third grid__item--desktop-up-quarter grid__item--wide-up-quarter gutter-bottom category-tile-grid-item layout-flex'][24]//div[@class='shop-tile__content shop-tile__metrics-container']//div[@class='shop-tile__metric'][1]//span[@class='shop-tile__metric__value text-bold'][1])"

DIODE BRAND
diodebrand.us
Art and photography

Private listing #572131
URL Hidden
Gifts and collectibles

检查清单：

print(price_list[:5])
print(name_list[:5])
print(website_type_list[:5])
print(revenue_list[:5])
print(traffic_list[:5])
print(profit_list[:5])
print(inventory_value_list[:5])

输出：

24
24
24
24
24
24
24

['$1,150USD', '$3,000USD', '$2,500USD', '$1,000USD', '$2,300USD']
['www.cosmicdetail.co.uk', 'prestige-timepiece.com', 'gomommyboutique.com', 'sunnysx.com', 'squishywishy.com']
['Automotive', 'Fashion and apparel', 'Toys and games', 'Fashion and apparel', 'Gifts and collectibles']
['$56', '$961', '$70', '$1.3K', '$403']
['111', '7.5K', '454', '2.8K', '2.6K']
['$50', '$1.0K', '$700', '$500', '$100']
['$1.8K', '', '', '', '']

"normalize-space(//div[@class='grid grid--equal-height']//div[@class='grid__item grid__item--tablet-up-third grid__item--desktop-up-quarter grid__item--wide-up-quarter gutter-bottom category-tile-grid-item layout-flex'][24]//div[@class='shop-tile__content shop-tile__metrics-container']//div[@class='shop-tile__metric'][1]//span[@class='shop-tile__metric__value text-bold'][1])"

DIODE BRAND
diodebrand.us
Art and photography

Private listing #572131
URL Hidden
Gifts and collectibles

如果要在控制台上尝试，请检查revenue的xpath：

revenue_xpath

输出：

24
24
24
24
24
24
24

['$1,150USD', '$3,000USD', '$2,500USD', '$1,000USD', '$2,300USD']
['www.cosmicdetail.co.uk', 'prestige-timepiece.com', 'gomommyboutique.com', 'sunnysx.com', 'squishywishy.com']
['Automotive', 'Fashion and apparel', 'Toys and games', 'Fashion and apparel', 'Gifts and collectibles']
['$56', '$961', '$70', '$1.3K', '$403']
['111', '7.5K', '454', '2.8K', '2.6K']
['$50', '$1.0K', '$700', '$500', '$100']
['$1.8K', '', '', '', '']

"normalize-space(//div[@class='grid grid--equal-height']//div[@class='grid__item grid__item--tablet-up-third grid__item--desktop-up-quarter grid__item--wide-up-quarter gutter-bottom category-tile-grid-item layout-flex'][24]//div[@class='shop-tile__content shop-tile__metrics-container']//div[@class='shop-tile__metric'][1]//span[@class='shop-tile__metric__value text-bold'][1])"

DIODE BRAND
diodebrand.us
Art and photography

Private listing #572131
URL Hidden
Gifts and collectibles

---

要单独获取段落，您可以执行以下操作：

from urllib.request import urlopen
from bs4 import BeautifulSoup

weblink = 'https://exchange.shopify.com/shops?sale_price=1000&shopify_shop_created_at=6m%2C0m'

def grabData(url):
    res = urlopen(url)
    soup = BeautifulSoup(res, "html.parser")

    for items in soup.find_all(class_="category-tile-grid-item"):
        title = items.find(class_="shop-tile__title").text
        name = items.find(class_="shop-tile__url").text
        category = items.find(class_="shop-tile__category").text
        print("{}\n{}\n{}\n".format(title,name,category))

if __name__ == '__main__':
    grabData(weblink)

输出：

24
24
24
24
24
24
24

['$1,150USD', '$3,000USD', '$2,500USD', '$1,000USD', '$2,300USD']
['www.cosmicdetail.co.uk', 'prestige-timepiece.com', 'gomommyboutique.com', 'sunnysx.com', 'squishywishy.com']
['Automotive', 'Fashion and apparel', 'Toys and games', 'Fashion and apparel', 'Gifts and collectibles']
['$56', '$961', '$70', '$1.3K', '$403']
['111', '7.5K', '454', '2.8K', '2.6K']
['$50', '$1.0K', '$700', '$500', '$100']
['$1.8K', '', '', '', '']

"normalize-space(//div[@class='grid grid--equal-height']//div[@class='grid__item grid__item--tablet-up-third grid__item--desktop-up-quarter grid__item--wide-up-quarter gutter-bottom category-tile-grid-item layout-flex'][24]//div[@class='shop-tile__content shop-tile__metrics-container']//div[@class='shop-tile__metric'][1]//span[@class='shop-tile__metric__value text-bold'][1])"

DIODE BRAND
diodebrand.us
Art and photography

Private listing #572131
URL Hidden
Gifts and collectibles

---

要单独获取段落，您可以执行以下操作：

from urllib.request import urlopen
from bs4 import BeautifulSoup

weblink = 'https://exchange.shopify.com/shops?sale_price=1000&shopify_shop_created_at=6m%2C0m'

def grabData(url):
    res = urlopen(url)
    soup = BeautifulSoup(res, "html.parser")

    for items in soup.find_all(class_="category-tile-grid-item"):
        title = items.find(class_="shop-tile__title").text
        name = items.find(class_="shop-tile__url").text
        category = items.find(class_="shop-tile__category").text
        print("{}\n{}\n{}\n".format(title,name,category))

if __name__ == '__main__':
    grabData(weblink)

输出：

24
24
24
24
24
24
24

['$1,150USD', '$3,000USD', '$2,500USD', '$1,000USD', '$2,300USD']
['www.cosmicdetail.co.uk', 'prestige-timepiece.com', 'gomommyboutique.com', 'sunnysx.com', 'squishywishy.com']
['Automotive', 'Fashion and apparel', 'Toys and games', 'Fashion and apparel', 'Gifts and collectibles']
['$56', '$961', '$70', '$1.3K', '$403']
['111', '7.5K', '454', '2.8K', '2.6K']
['$50', '$1.0K', '$700', '$500', '$100']
['$1.8K', '', '', '', '']

"normalize-space(//div[@class='grid grid--equal-height']//div[@class='grid__item grid__item--tablet-up-third grid__item--desktop-up-quarter grid__item--wide-up-quarter gutter-bottom category-tile-grid-item layout-flex'][24]//div[@class='shop-tile__content shop-tile__metrics-container']//div[@class='shop-tile__metric'][1]//span[@class='shop-tile__metric__value text-bold'][1])"

DIODE BRAND
diodebrand.us
Art and photography

Private listing #572131
URL Hidden
Gifts and collectibles

---

非常感谢你这么做。我决定以这种方式实施它，并对其进行扩展。我的问题是，例如，我如何获得收入而不是流量？为什么它选择流量而不是收入，因为收入在你申报的方式中是第一位的。非常感谢你！不客气！我再次更新了代码。我还添加了所有的表格参数和网站类型。再次非常感谢！很抱歉打扰您，您有什么办法可以帮助我吗：非常感谢您的帮助。我决定以这种方式实施它，并对其进行扩展。我的问题是，例如，我如何获得收入而不是流量？为什么它选择流量而不是收入，因为收入在你申报的方式中是第一位的。非常感谢你！不客气！我再次更新了代码。我还添加了所有的表格参数和网站类型。再次非常感谢！很抱歉打扰您-您有什么办法可以在这里帮助我：