Question

我已经完成了Wikipedia信息框的剪贴，但是我不知道如何将htht数据存储在csv文件中。请帮帮我。

from bs4 import BeautifulSoup as bs
from urllib.request import urlopen


def infobox(query) :
    query = query
    url = 'https://en.wikipedia.org/wiki/'+query
    raw = urlopen(url)
    soup = bs(raw)
    table = soup.find('table',{'class':'infobox vcard'})
    for tr in table.find_all('tr') :
        print(tr.text)
infobox('Infosys')

Answer 1

您必须收集所需的数据并写入csv文件，您可以使用csv模块，请参见以下示例：

from bs4 import BeautifulSoup as bs
from urllib import urlopen
import csv


def infobox(query) :
    query = query
    content_list = []
    url = 'https://en.wikipedia.org/wiki/'+query
    raw = urlopen(url)
    soup = bs(raw)
    table = soup.find('table',{'class':'infobox vcard'})
    for tr in table.find_all('tr') :
        if len(tr.contents) > 1:
            content_list.append([tr.contents[0].text.encode('utf-8'), tr.contents[1].text.encode('utf-8')])
        elif tr.text:
            content_list.append([tr.text.encode('utf-8')])
    write_csv_file(content_list)

def write_csv_file(content_list):
    with open(r'd:\Test.csv', mode='wb') as csv_file:
        writer = csv.writer(csv_file, delimiter=',')
        writer.writerows(content_list)

infobox('Infosys')

Answer 2

这里概述了如何测试行中是否有标题和表格单元格元素以确保两列（可以扩展为仅写入td行以填充if结构中的第一列）。对于查找更干净的输出，我使用略有不同的编码语法，对于select使用的元素查找速度要比查找并利用熊猫来生成csv更快。

import requests
from bs4 import BeautifulSoup as bs
import pandas as pd
url = 'https://en.wikipedia.org/wiki/'+ 'Infosys'
headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/27.0.1453.93 Safari/537.36', 'Referer': 'https://www.nseindia.com/'}
r = requests.get(url,  headers=headers)
soup = bs(r.content,'lxml')
table =soup.select_one('.infobox.vcard')
rows = table.find_all('tr')
output = []
for row in rows:
    if len(row.select('th, td')) == 2:
        outputRow = [row.select_one('th').text, row.select_one('td').text, [item['href'] for item in row.select('td a')] if row.select_one('td a') is not None else '']
        outputRow[2] = ['https://en.wikipedia.org/wiki/Infosys' + item if item[0] == '#' else 'https://en.wikipedia.org' + item for item in outputRow[2]]
        output.append(outputRow)
df = pd.DataFrame(output)    
df.to_csv(r'C:\Users\User\Desktop\Data.csv', sep=',', encoding='utf-8-sig',index = False )

如何剪贴维基百科信息框并将其存储到csv文件中

2 个答案: