使用 Python/BeautifulSoup 解析后不写入 CSV

Question

我有一种感觉，我犯了一个愚蠢的错误。我正在尝试从网站上抓取一些数据，我可以解析数据，但它不会写入 csv。我是 python 的初学者，对此我摸不着头脑。

到目前为止，这是我的代码：

import requests
import csv
from  bs4 import BeautifulSoup

base_url = "http://www.example.com/"

total_pages = 100

def parse_content(r):
    soup = BeautifulSoup(r.content,'lxml')
    g_data = soup.find_all('ul', {"class": "searchResults"})

    for item in g_data:
        for li in item.findAll('li'):
            for resultnameh2 in li.findAll('h2'):
                for resultname in resultnameh2.findAll('a'):
                    cname = resultname.text
                    
        for resultAddress in li.findAll('p', {"class": "resultAddress"}):
            caddress = resultAddress.text.replace('Get directions','').strip()  
            
        for resultContact in li.findAll('ul', {"class": "resultContact"}):
            for resultContact in li.findAll('a', {"class": "resultMainNumber"}):
                ccontact = resultContact.text

for page in range(1, total_pages):
    response = requests.get(base_url + '/' + str(page))
    if response.status_code != 200:
        break

    parse_content(response)
    csvdata = parse_content(response)
    
    with open('index.csv', 'a') as csv_file:  
        writer = csv.writer(csv_file)
        writer.writerow([csvdata])

Answer 1

cname、caddress、ccontact 的值已在函数 parse_content 的上下文中设置，因此在 csv 写入器的 for 循环中不可用。

您要么需要返回这些值，要么需要在 parse_content 方法中移动 csv 写入器。

Answer 2

你需要返回值

import requests
import csv
from  bs4 import BeautifulSoup

base_url = "http://www.example.com/"

total_pages = 100

def parse_content(r): # you are not returning anything from this function, I will change this function so it will return required values.
    cname=[]
    caddress=[]
    ccontact=[]
    soup = BeautifulSoup(r.content,'lxml')
    g_data = soup.find_all('ul', {"class": "searchResults"})

    for item in g_data:
        for li in item.findAll('li'):
            for resultnameh2 in li.findAll('h2'):
                for resultname in resultnameh2.findAll('a'):
                    cname.append(resultname.text) # As it is list you need to append all these values

        for resultAddress in li.findAll('p', {"class": "resultAddress"}):
            caddress.append(resultAddress.text.replace('Get directions','').strip())  

        for resultContact in li.findAll('ul', {"class": "resultContact"}):
            for resultContact in li.findAll('a', {"class": "resultMainNumber"}):
                ccontact.append(resultContact.text)

    return cname,caddress,ccontact

for page in range(1, total_pages):
    response = requests.get(base_url + '/' + str(page))
    if response.status_code != 200:
        break

    parse_content(response)
    cname,caddress,ccontact = parse_content(response)
    print(cname)
    print(caddress)
    print(ccontact)
    #print whatever you like from above lists 
    with open('index.csv', 'a') as csv_file:  
        writer = csv.writer(csv_file)
        writer.writerow([csvdata])