非常简单,找到网页,获取网页内容,xpath查找,输出
https://book.douban.com/subject_search?search_text=python&cat=1001&start=%s0
from selenium import webdriver
import time
from lxml import etree
#获取网页内容
def get_web(url):
driver = webdriver.Chrome()
driver.get(url)
#强制等待网页加载
time.sleep(10)
driver.save_screenshot('douban.png')
#保存网页文件
fn = 'douban.html'
with open(fn,'w',encoding='utf-8') as f:
f.write(driver.page_source)
content_parse(fn)
#退出浏览器
driver.quit()
#解析网页
def content_parse(fn):
#读取网页内容
with open(fn,'r',encoding='utf-8')as f:
html = f.read()
print(type(html))
tree = etree.HTML(html)
#通过书籍标签查找书名
books = tree.xpath("//div[@class='item-root']")
for book in books:
book_name = book.xpath(".//div[@class='title']/a")
print(book_name[0].text)
if __name__ == '__main__':
url ='https://book.douban.com/subject_search?search_text=python&cat=1001&start=%s0'
get_web(url)