根據一個爬取豆瓣電影排名的小應用，來簡單使用etree和request庫。

etree使用xpath語法。

import requests
import ssl
from lxml import etree


ssl._create_default_https_context = ssl._create_unverified_context

session = requests.Session()
for id in range(0, 251, 25):
    URL = 'https://movie.douban.com/top250/?start=' + str(id)
    req = session.get
 
(URL)
    # 設定網頁編碼格式
    req.encoding = 'utf8'
    # 將request.content 轉化為 Element
    root = etree.HTML(req.content)
    # 選取 ol/li/div[@class="item"] 不管它們在文件中的位置
    items = root.xpath('//ol/li/div[@class="item"]')
    for item in items:
        # 注意可能只有中文名，沒有英文名；可能沒有quote簡評
        rank, name, alias, rating_num, quote
 
, url = "", "", "", "", "", ""
        try:
            url = item.xpath('./div[@class="pic"]/a/@href')[0]
            rank = item.xpath('./div[@class="pic"]/em/text()')[0]
            title = item.xpath('./div[@class="info"]//a/span[@class="title"]/text()')
            name = title[0].encode('gb2312', 'ignore').decode('gb2312'
 
)
            alias = title[1].encode('gb2312', 'ignore').decode('gb2312') if len(title) == 2 else ""
            rating_num = item.xpath('.//div[@class="bd"]//span[@class="rating_num"]/text()')[0]
            quote_tag = item.xpath('.//div[@class="bd"]//span[@class="inq"]')
            if len(quote_tag) is not 0:
                quote = quote_tag[0].text.encode('gb2312', 'ignore').decode('gb2312').replace('\xa0', '')
            # 輸出 排名，評分，簡介
            print(rank, rating_num, quote)
            # 輸出 中文名，英文名
            print(name.encode('gb2312', 'ignore').decode('gb2312'),
                  alias.encode('gb2312', 'ignore').decode('gb2312').replace('/', ','))
        except:
            print('faild!')
            pass

程式執行結果：