python Selenium爬取
文章目录
目标网站：
https://spa2.scrape.center/
这个网站是一个电影评分网站，采用selenium进行爬取
第一步,我们先导入相应的库
import json
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
import logging
from urllib.parse import urljoin
from os import makedirs
from os.path import exists
其实，我们这些库在我们写代码的时候，需要什么就导入什么，不过，这里就直接给出，了解一下这些库。大部分是selenium的一些库
第二步：初始话浏览器
from selenium.webdriver import Chrome#导入浏览器的包
#打开浏览器
web=Chrome()
#打开浏览器，请求网站
web.get('https://www.baidu.com')
可以看我的另外一篇文章
https://blog.csdn.net/Deng872347348/article/details/112688855#comments_20429011
为了避免代码的冗余，我们代码采用的是def封装函数的，减少代码的重写，最好的是通过面向对象对代码进行编写，这样子可以最大化的避免代码的重写。
定义通用爬取的函数方法:
def scrape_page(url, condition, locator): # 定义通用爬取方法
logging.info('scraping %s', url)
try:
browser.get(url)
wait.until(condition(locator)) # 等待
except TimeoutException: # 报错处理
logging.error('error occurred while scraping %s', url, exc_info=True)
定义一个函数，获取爬取的开始url:
def scrapge_index(page):
url = INDEX_URL.format(page=page) # 完善url
scrape_page(url, condition=EC.visibility_of_all_elements_located, # 元素可见方法
locator=(By.CSS_SELECTOR, '#index .item')) # CSS定位元素
定义详情页：
def scrape_detail(url):
scrape_page(url, condition=EC.presence_of_element_located,
locator=(By.TAG_NAME, 'h2'))
详情页详细爬取：
def parse_detail():
url = browser.current_url # 获取当前链接
name = browser.find_element_by_tag_name('h2').text
categories = [element.text for element in browser.find_elements_by_css_selector('.categories button span')]
cover = browser.find_element_by_css_selector('.cover').get_attribute('src')
score = browser.find_element_by_class_name('score').text
drama = browser.find_element_by_css_selector('.drama p').text
return {
'url': url,
'name': name,
'categories': categories,
'cover': cover,
'score': score,
'drama': drama
}
获取电影详情链接
def parse_index(): # 获取电影详情链接
elements = browser.find_elements_by_css_selector('#index .item .name')
for element in elements:
href = element.get_attribute('href')
yield urljoin(INDEX_URL, href)
存储函数：
def save_data(data): # 储存
name = data.get('name')
data_path = f'{RESULTS_DIR}/{name}.json'
json.dump(data, open(data_path, 'w', encoding='utf-8'), ensure_ascii=False, indent=2)
运行的主函数：
def main():
try:
for page in range(1, TOTAL_PAGE + 1):
scrapge_index(page)
detail_urls = parse_index()
for detail_url in list(detail_urls):
logging.info('get detail url %s', detail_url)
scrape_detail(detail_url)
detail_data = parse_detail()
save_data(detail_data)
logging.info('detail data %s', detail_data)
finally:
browser.close()
if __name__ == '__main__':
main()
完整代码 ：
import json
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
import logging
from urllib.parse import urljoin
from os import makedirs
from os.path import exists
logging.basicConfig(level=logging.INFO,
format='%(asctime)s - %(levelname)s: %(message)s') # 日志配置
INDEX_URL = 'https://spa2.scrape.center/page/{page}' # 电影列表页面
TIME_OUT = 10 # 等待时长
TOTAL_PAGE = 10 # 页数
browser = webdriver.Chrome() # 初始化浏览器
wait = WebDriverWait(browser, TIME_OUT) # 配置页面加载最长等待时间
def scrape_page(url, condition, locator): # 定义通用爬取方法
logging.info('scraping %s', url)
try:
browser.get(url)
wait.until(condition(locator)) # 等待
except TimeoutException: # 报错处理
logging.error('error occurred while scraping %s', url, exc_info=True)
def scrapge_index(page):
url = INDEX_URL.format(page=page) # 完善url
scrape_page(url, condition=EC.visibility_of_all_elements_located, # 元素可见方法
locator=(By.CSS_SELECTOR, '#index .item')) # CSS定位元素
def scrape_detail(url):
scrape_page(url, condition=EC.presence_of_element_located,
locator=(By.TAG_NAME, 'h2'))
def parse_detail():
url = browser.current_url # 获取当前链接
name = browser.find_element_by_tag_name('h2').text
categories = [element.text for element in browser.find_elements_by_css_selector('.categories button span')]
cover = browser.find_element_by_css_selector('.cover').get_attribute('src')
score = browser.find_element_by_class_name('score').text
drama = browser.find_element_by_css_selector('.drama p').text
return {
'url': url,
'name': name,
'categories': categories,
'cover': cover,
'score': score,
'drama': drama
}
def parse_index(): # 获取电影详情链接
elements = browser.find_elements_by_css_selector('#index .item .name')
for element in elements:
href = element.get_attribute('href')
yield urljoin(INDEX_URL, href)
RESULTS_DIR = 'results' # 定义目录
exists(RESULTS_DIR) or makedirs(RESULTS_DIR) # 确定路径在不在，没有新建
def save_data(data): # 储存
name = data.get('name')
data_path = f'{RESULTS_DIR}/{name}.json'
json.dump(data, open(data_path, 'w', encoding='utf-8'), ensure_ascii=False, indent=2)
def main():
try:
for page in range(1, TOTAL_PAGE + 1):
scrapge_index(page)
detail_urls = parse_index()
for detail_url in list(detail_urls):
logging.info('get detail url %s', detail_url)
scrape_detail(detail_url)
detail_data = parse_detail()
save_data(detail_data)
logging.info('detail data %s', detail_data)
finally:
browser.close()
if __name__ == '__main__':
main()
如果你运行出行浏览器窗口闪退，代码出行下面的错误的话，说明你的那个chrome driver的版本和谷歌浏览器的版本不一样
selenium.common.exceptions.SessionNotCreatedException: Message: session not created: This version of ChromeDriver only supports Chrome version 92
Current browser version is 99.0.4844.74 with binary path C:\Program Files\Google\Chrome\Application\chrome.exe
可以去谷歌浏览器设置里面查看自己的谷歌浏览器更新到那个版本了，
如图
提供一个网站下载chrome driver的驱动
https://chromedriver.storage.googleapis.com/index.html
可以下载最近谷歌浏览器更新的代码，有mac 苹果系统的，linux的版本