首页 > 解决方案 > 将清理后的 BS4 数据写入 csv 文件

问题描述

from selenium import webdriver

from bs4 import BeautifulSoup

import csv

chrome_path = r"C:\Users\chromedriver_win32\chromedriver.exe"

driver = webdriver.Chrome(chrome_path)

driver.get('http://www.yell.com')

search = driver.find_element_by_id("search_keyword")

search.send_keys("plumbers")

place = driver.find_element_by_id("search_location")

place.send_keys("London")

driver.find_element_by_xpath("""//*[@id="searchBoxForm"]/fieldset/div[1]/div[3]/button""").click()

soup = BeautifulSoup(driver.page_source, 'html.parser')

for names in soup.find_all("span", {"class": "businessCapsule--name"}):
    print(names.text)

Output = soup.find_all("span", {"class": "businessCapsule--name"})

with open('comple16.csv', 'w') as csv_file:
    csv.register_dialect('custom', delimiter='\n', quoting=csv.QUOTE_NONE, escapechar='\\')
    writer = csv.writer(csv_file, 'custom')
    row = Output
    writer.writerow(row)

目前代码在 csv file = class": "businessCapsule-- (scraped text) 中产生这个

我只想将抓取的文本打印到 CSV 文件中(不带标签)

请帮忙。

标签: pythonseleniumbeautifulsoup

解决方案


from selenium import webdriver

from bs4 import BeautifulSoup`

import csv

chrome_path = r"C:\Users\chromedriver_win32\chromedriver.exe"

driver = webdriver.Chrome(chrome_path)

driver.get('http://www.yell.com')

search = driver.find_element_by_id("search_keyword")

search.send_keys("plumbers")

place = driver.find_element_by_id("search_location")

place.send_keys("London")

driver.find_element_by_xpath("""//*[@id="searchBoxForm"]/fieldset/div[1]/div[3]/button""").click()

soup = BeautifulSoup(driver.page_source, 'html.parser')

Output = []
for names in soup.find_all("span", {"class": "businessCapsule--name"}):
    Output.append(names.text)

with open('comple16.csv', 'w') as csv_file:
    csv.register_dialect('custom', delimiter='\n', quoting=csv.QUOTE_NONE, escapechar='\\')
    writer = csv.writer(csv_file, 'custom')
    row = Output
    writer.writerow(row)

推荐阅读