我不知道你到底想如何保存这些预览链接中的信息,所以我把这部分留给你。修改这个脚本以下载所有这些脚本也很简单
.docx
文件,而不是仅仅抓住预览链接。
import json
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.common.exceptions import (
NoSuchElementException,
WebDriverException
)
base_url = 'http://www.produktresume.dk'
chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--headless')
driver = webdriver.Chrome(chrome_options=chrome_options)
driver.get('{}/AppBuilder/search'.format(base_url))
result = []
while True:
soup = BeautifulSoup(driver.page_source, 'lxml')
preview_links = [base_url + link['href']
for link in soup.find_all('a', class_='preview_link')]
result.extend(preview_links)
try:
element = driver.find_element_by_link_text('Næste')
element.click()
except (NoSuchElementException, WebDriverException):
break
driver.quit()
with open('preview_links.json', 'w') as f:
json.dump(result, f, indent=2)
preview_links.json
