Python爬取豆瓣电影数据并且提取值xpath和lxml模块（代码）

from lxml import etree
import requests

url = "https://movie.douban.com/chart"

headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.81 Safari/537.36"
}
response = requests.get(url,headers=headers)
html_str = response.content.decode()

#print(html_str)

html = etree.HTML(html_str)
print(html)

#1.获取所有的电影的URL地址
#url_list = html.xpath("//div[@class='indent']/div/table//div[@class='pl2']/a/@href")
#print(url_list)

#2.所有图片的地址
#img_list = html.xpath("//div[@class='indent']/div/table//a[@class='nbg']/img/@src")
#print(img_list)
ret1 = html.xpath("//div[@class='indent']/div/table")
print(ret1)
for table in ret1:
    item = {}
    item["title"] = table.xpath(".//div[@class='pl2']/a/text()")[0].replace("/","").strip()
    item["href"] = table.xpath(".//div[@class='pl2']/a/@href")[0]
    item["img"] = table.xpath(".//a[@class='nbg']/img/@src")[0]
    item["comment_num"] = table.xpath(".//span[@class='pl']/text()")[0]
    item["rating_num"] = table.xpath(".//span[@class='rating_nums']/text()")[0]
    print(item)