爬取豆瓣Top250 - 2

"""
TODO 显示影片基本信息
TODO 访问豆瓣电影Top250（https://movie.douban.com/top250?start=0），
TODO 获取每部电影的中文片名、排名、评分及其对应的链接，按照“排名-中文片名-评分-链接”的格式显示在屏幕上。
"""


import requests
from lxml import etree

def get_html(url):
    header = { 'User-Agent': 'Mozilla/5.0' }
    return requests.get(url=url, headers=header).text

def parser_html(response):
    # TODO 将HTML文本解析为lxml的Element对象
    html = etree.HTML(response)

    # TODO 使用xpath选择器提取信息
    li_list = html.xpath('//ol[@class="grid_view"]/li')

    for li in li_list:
        # TODO 排名
        ranking = li.xpath('.//em/text()')[0]
        # TODO 片名
        title = li.xpath('.//span[@class="title"]/text()')[0]
        # TODO 评分
        score = li.xpath('.//span[@class="rating_num"]/text()')[0]
        # TODO 链接
        href = li.xpath('.//a/@href')[0]
        # TODO 输出排名-中文片名-评分-链接
        print(ranking, '-', title, '-', score, '-', href)

if __name__ == '__main__':
    base_url = 'https://movie.douban.com/top250?start={}&filter='
    # TODO 爬取前250部电影信息
    url_list = [base_url.format(i) for i in range(0, 250, 25)]
    for page_url in url_list:
        html_content = get_html(page_url)
        parser_html(html_content)

"""
TODO 访问豆瓣电影Top250（https://movie.douban.com/top250?start=0），
TODO 在问题1的基础上，获取每部电影的导演、编剧、主演、类型、上映时间、片长、评分人数以及剧情简介等信息，
TODO 并将获取到的信息以CSV格式保存至本地文件中。
"""

import requests
from bs4 import BeautifulSoup
import csv

url_base = "https://movie.douban.com/top250?start={}&filter="
headers = {"user-agent":"Mozilla/5.0"}

with open('movie_info.csv', 'w', newline='', encoding='utf-8') as csvfile:
    fieldnames = ['导演', '编剧', '主演', '类型', '上映时间', '片长', '评分人数', '剧情简介']
    writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
    writer.writeheader()

    # TODO 分页爬取
    for i in range(0, 250, 25):
        url = url_base.format(i)

        resp = requests.get(url=url, headers=headers)
        soup = BeautifulSoup(resp.content, "lxml")
        divs = soup.find_all("div", class_="item")

        for index, li in enumerate(divs):
            href = li.find("a").get('href')
            resp_detail = requests.get(url=href, headers=headers)
            soup_detail = BeautifulSoup(resp_detail.content, "lxml")

            # TODO 导演
            director_info = soup_detail.find("span", class_="pl")
            director_name = director_info.find_next("span").text.split(":")[0].strip() if director_info else None
            print(director_name)

            # TODO 编剧
            writer_info = soup_detail.find("span", class_="attrs")
            writer_name = writer_info.find_next("span").text.split(":")[1].strip() if writer_info else None
            print(writer_name)

            # TODO 主演
            spans = soup_detail.find_all("span", class_="attrs")
            actors = spans[2].text if len(spans) >= 3 else None
            print(actors)

            # TODO 类型
            genres_name = soup_detail.find("span", property="v:genre")
            genres_name = genres_name.find_next("span").text if genres_name else None
            print(genres_name)

            # TODO 上映时间
            release_date = soup_detail.find("span", property="v:initialReleaseDate")
            release_date = release_date.find_next("span").text if release_date else None
            print(release_date)

            # TODO 片长
            runtime = soup_detail.find("span", property="v:runtime")
            runtime = runtime.text if runtime else None
            print(runtime)

            # TODO 评分人数
            rating_count = soup_detail.find("span", property="v:votes")
            rating_count = rating_count.text if rating_count else None
            print(rating_count)

            # TODO 剧情简介
            summary_span = soup_detail.find("span", property="v:summary")
            summary = summary_span.text.strip() if summary_span else None
            summary = summary.replace('\n', ' ').replace('\r', '')
            print(summary)
            print("-------------------------------------------------------------------")

            # TODO 将数据写入 CSV 文件
            movie_info = {
                '导演': director_name,
                '编剧': writer_name,
                '主演': actors,
                '类型': genres_name,
                '上映时间': release_date,
                '片长': runtime,
                '评分人数': rating_count,
                '剧情简介': summary
            }
            writer.writerow(movie_info)

    print("数据已保存到 movie_info.csv")