python 网络爬虫 1.2 获取豆瓣TOP250电影的中英文名、港台名、导演、上映年份、电影分类以及评分，将数据存入文档。

题目：
获取豆瓣TOP250电影的中英文名、港台名、导演、上映年份、电影分类以及评分，将数据存入文档。
代码：

import codecs
import csv
import re

from requests_html import HTMLSession

base_url = "h  t  t  p  s://movie.douban.com/top250?start=" # 自己处理一下空格，没空格发不了
# 获取请求对象
session = HTMLSession()
result_list = []


def filter(s):
    if s:
        s = s.strip()
        s = re.sub('\s+', ' ', s)
        s = s.replace(" / ", "/")
        if s[0] == "/":
            s = s[1:]
        s = s.strip()
    return s


for i in range(0, 10):
    url = base_url + str(i * 25)
    response = session.get(url)
    html = response.html
    div = html.xpath('//*[@class="grid_view"]', first=True)
    div_list = div.xpath('//li')
    for d in div_list:
        z_name = filter(d.xpath('//div/div[2]/div[1]/a/span[1]/text()', first=True))
        e_name = filter(d.xpath('//div/div[2]/div[1]/a/span[2]/text()', first=True))
        g_name = filter(d.xpath('//div/div[2]/div[1]/a/span[3]/text()', first=True))
        info_list = d.xpath('//div/div[2]/div[2]/p/text()')
        if len(info_list) > 1:
                txt1 = info_list[0].strip()
                if "主" in txt1:
                    director = txt1[3:txt1.index("主")].strip()
                else:
                    director = txt1[3:]
                txt_info = info_list[1].strip().split("/")
                year = txt_info[0].strip()
                _type = txt_info[2].strip()
                rating_num = d.xpath('.//span[@class="rating_num"]/text()', first=True)
                result_list.append({
                    "中文名": z_name,
                    "英文名": e_name,
                    "港台名": g_name,
                    "导演": director,
                    "上映年份": year,
                    "分类": _type,
                    "评分": rating_num,
                })
        else:
            print(url, z_name, info_list)
csv_file = codecs.open('data/movie_test.csv', 'w', encoding='utf-8')
writer = csv.writer(csv_file)
for d in result_list:
    writer.writerow((d['中文名'], d['英文名'], d['港台名'], d['导演'], d['上映年份'], d['分类'], d['评分']))
csv_file.close()

输出结果：