0

该代码获取 fitgirl 中可用的所有游戏，并制作一个包含每个游戏中评论数量的字典。评论获取部分需要 selenium，因为它依赖于他们的 disqus 服务。我可以以某种方式优化流程吗？

import bs4
from selenium import webdriver
from selenium.webdriver import ChromeOptions
from selenium.common import exceptions
import requests

path = 'C:\\ChromeDriver\\chromedriver.exe'

options = ChromeOptions()
options.add_argument('--headless')
options.add_argument('--ignore-certificate-errors')
options.add_argument('--ignore-ssl-errors')
options.add_argument('log-level=3')
options.add_experimental_option('excludeSwitches', ['enable-logging'])

info_dict = {}

for page_number in range(1, 31):

    url = f'https://fitgirl-repacks.site/all-my-repacks-a-z/?lcp_page0={page_number}#lcp_instance_0'

    response1 = requests.get(url)

    index_site = bs4.BeautifulSoup(response1.content, 'lxml')

    ul = index_site.find('ul', class_='lcp_catlist')
    for li in ul.children:
        site_url = li.a['href']
        try:
            driver = webdriver.Chrome(executable_path=path, options=options)
            driver.get(site_url)

            page_data = driver.page_source

            site = bs4.BeautifulSoup(page_data, 'lxml')

            comment = site.find('span', class_='comments-link').a.string
            title = site.find('header', class_='entry-header').h1.string
            print(title + ' ' + comment)

            info_dict[title] = comment
        except exceptions.SessionNotCreatedException:
            print('pass')
        # driver.close()

driver.close()

print(info_dict)
4

0 回答 0