python BeautifulSoup解析表

我正在学习 python requests 和 BeautifulSoup。作为练习,我选择编写一个快速的 NYC 停车罚单解析器。我能够得到一个非常难看的 html 响应。我需要获取 lineItemsTable 并解析所有票证。

您可以通过访问此处复制页面: https://paydirect.link2gov.com/NYCParking-Plate/ItemSearch 并输入 NYT630134C

soup = BeautifulSoup(plateRequest.text)
#print(soup.prettify())
#print soup.find_all('tr')

table = soup.find("table", { "class" : "lineItemsTable" })
for row in table.findAll("tr"):
    cells = row.findAll("td")
    print cells

有人可以帮我吗?简单地查找所有 tr 并没有让我到任何地方。

stack overflow python BeautifulSoup parsing table
原文答案
author avatar

接受的答案

干得好:

data = []
table = soup.find('table', attrs={'class':'lineItemsTable'})
table_body = table.find('tbody')

rows = table_body.find_all('tr')
for row in rows:
    cols = row.find_all('td')
    cols = [ele.text.strip() for ele in cols]
    data.append([ele for ele in cols if ele]) # Get rid of empty values

这给了你:

[ [u'1359711259', u'SRF', u'08/05/2013', u'5310 4 AVE', u'K', u'19', u'125.00', u'$'], 
  [u'7086775850', u'PAS', u'12/14/2013', u'3908 6th Ave', u'K', u'40', u'125.00', u'$'], 
  [u'7355010165', u'OMT', u'12/14/2013', u'3908 6th Ave', u'K', u'40', u'145.00', u'$'], 
  [u'4002488755', u'OMT', u'02/12/2014', u'NB 1ST AVE @ E 23RD ST', u'5', u'115.00', u'$'], 
  [u'7913806837', u'OMT', u'03/03/2014', u'5015 4th Ave', u'K', u'46', u'115.00', u'$'], 
  [u'5080015366', u'OMT', u'03/10/2014', u'EB 65TH ST @ 16TH AV E', u'7', u'50.00', u'$'], 
  [u'7208770670', u'OMT', u'04/08/2014', u'333 15th St', u'K', u'70', u'65.00', u'$'], 
  [u'$0.00nnnPayment Amount:']
]

需要注意的几点:

  • 上面输出的最后一行,付款金额不是表格的一部分,但表格的布局是这样的。您可以通过检查列表的长度是否小于 7 来将其过滤掉。
  • 每行的最后一列必须单独处理,因为它是一个输入文本框。

答案:

作者头像

更新的答案

如果程序员只对从网页中解析表格感兴趣,他们可以使用 pandas 方法 pandas.read_html

假设我们要从网站中提取 GDP 数据表: https://worldpopulationreview.com/countries/countries-by-gdp/#worldCountries

然后以下代码完美地完成了这项工作(不需要漂亮的汤和花哨的 html):

仅使用pandas

# sometimes we can directly read from the website
url = "https://en.wikipedia.org/wiki/AFI%27s_100_Years...100_Movies#:~:text=%20%20%20%20Film%20%20%20,%20%204%20%2025%20more%20rows%20"
df = pd.read_html(url)
df.head()

使用 pandas 和 requests(更一般的情况)


# if pd.read_html does not work, we can use pd.read_html using requests.
import pandas as pd
import requests

url = "https://worldpopulationreview.com/countries/countries-by-gdp/#worldCountries"

r = requests.get(url)
df_list = pd.read_html(r.text) # this parses all the tables in webpages to a list
df = df_list[0]
df.head()

所需模块

pip install lxml
pip install requests
pip install pandas

输出

First five lines of the table from the Website

作者头像

解决了,这就是你解析他们的 html 结果的方式:

table = soup.find("table", { "class" : "lineItemsTable" })
for row in table.findAll("tr"):
    cells = row.findAll("td")
    if len(cells) == 9:
        summons = cells[1].find(text=True)
        plateType = cells[2].find(text=True)
        vDate = cells[3].find(text=True)
        location = cells[4].find(text=True)
        borough = cells[5].find(text=True)
        vCode = cells[6].find(text=True)
        amount = cells[7].find(text=True)
        print amount
作者头像

这是通用 <table> 的工作示例。 ( question links-broken )

按 GDP(国内生产总值)从 here 个国家提取表格。

htmltable = soup.find('table', { 'class' : 'table table-striped' })
# where the dictionary specify unique attributes for the 'table' tag

tableDataText 函数解析以标签 <table> 开头的 html 段,后跟多个 <tr> (表格行)和内部 <td> (表格数据)标签。它返回具有内列的行列表。第一行只接受一个 <th> (表头/数据)。

def tableDataText(table):       
    rows = []
    trs = table.find_all('tr')
    headerow = [td.get_text(strip=True) for td in trs[0].find_all('th')] # header row
    if headerow: # if there is a header row include first
        rows.append(headerow)
        trs = trs[1:]
    for tr in trs: # for every table row
        rows.append([td.get_text(strip=True) for td in tr.find_all('td')]) # data row
    return rows

使用它我们得到(前两行)。

list_table = tableDataText(htmltable)
list_table[:2]

[['Rank',
  'Name',
  "GDP (IMF '19)",
  "GDP (UN '16)",
  'GDP Per Capita',
  '2019 Population'],
 ['1',
  'United States',
  '21.41 trillion',
  '18.62 trillion',
  '$65,064',
  '329,064,917']]

这可以很容易地转换为 pandas.DataFrame 以获得更高级的工具。

import pandas as pd
dftable = pd.DataFrame(list_table[1:], columns=list_table[0])
dftable.head(4)

pandas DataFrame html table output

作者头像
from behave import *
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as ec
import pandas as pd
import requests
from bs4 import BeautifulSoup
from tabulate import tabulate

class readTableDataFromDB: 
    def LookupValueFromColumnSingleKey(context, tablexpath, rowName, columnName):
        print("element present readData From Table")
        element = context.driver.find_elements_by_xpath(tablexpath+"/descendant::th")
        indexrow = 1
        indexcolumn = 1
        for values in element:
            valuepresent = values.text
            print("text present here::"+valuepresent+"rowName::"+rowName)
            if valuepresent.find(columnName) != -1:
                 print("current row"+str(indexrow) +"value"+valuepresent)
                 break
            else:
                 indexrow = indexrow+1    

        indexvalue = context.driver.find_elements_by_xpath(
            tablexpath+"/descendant::tr/td[1]")
        for valuescolumn in indexvalue:
            valuepresentcolumn = valuescolumn.text
            print("Team text present here::" +
                  valuepresentcolumn+"columnName::"+rowName)
            print(indexcolumn) 
            if valuepresentcolumn.find(rowName) != -1:
                print("current column"+str(indexcolumn) +
                      "value"+valuepresentcolumn)
                break
            else:
                indexcolumn = indexcolumn+1

        print("index column"+str(indexcolumn))
        print(tablexpath +"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
        #lookupelement = context.driver.find_element_by_xpath(tablexpath +"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
        #print(lookupelement.text)
        return context.driver.find_elements_by_xpath(tablexpath+"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")

    def LookupValueFromColumnTwoKeyssss(context, tablexpath, rowName, columnName, columnName1):
        print("element present readData From Table")
        element = context.driver.find_elements_by_xpath(
            tablexpath+"/descendant::th")
        indexrow = 1
        indexcolumn = 1
        indexcolumn1 = 1
        for values in element:
            valuepresent = values.text
            print("text present here::"+valuepresent)
            indexrow = indexrow+1
            if valuepresent == columnName:
                print("current row value"+str(indexrow)+"value"+valuepresent)
                break

        for values in element:
            valuepresent = values.text
            print("text present here::"+valuepresent)
            indexrow = indexrow+1
            if valuepresent.find(columnName1) != -1:
                print("current row value"+str(indexrow)+"value"+valuepresent)
                break

        indexvalue = context.driver.find_elements_by_xpath(
            tablexpath+"/descendant::tr/td[1]")
        for valuescolumn in indexvalue:
            valuepresentcolumn = valuescolumn.text
            print("Team text present here::"+valuepresentcolumn)
            print(indexcolumn)
            indexcolumn = indexcolumn+1
            if valuepresent.find(rowName) != -1:
                print("current column"+str(indexcolumn) +
                      "value"+valuepresentcolumn)
                break
        print("indexrow"+str(indexrow))
        print("index column"+str(indexcolumn))
        lookupelement = context.driver.find_element_by_xpath(
            tablexpath+"//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
        print(tablexpath +
              "//descendant::tr["+str(indexcolumn)+"]/td["+str(indexrow)+"]")
        print(lookupelement.text)
        return context.driver.find_element_by_xpath(tablexpath+"//descendant::tr["+str(indexrow)+"]/td["+str(indexcolumn)+"]")