python入门之爬虫---获取豆瓣TOP250的电影

主要使用requests模块和BeautifualSoup4模块

import requests
import bs4


def open_url(url):
    # 使用代理
    # proxies = {"http":"127.0.0.1:1000","http":"127.0.0.1:1080"}
    headers = dict()
    headers["user-agent"] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) \
    AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.110 Safari/537.36"
    res = requests.get(url=url, headers=headers)
    return res


#  找出一共有多少个页面,因为一页只有２５个电影，所以需要获取不同的页面
def find_depth(res):
    soup = bs4.BeautifulSoup(res.text, "html.parser")
    depth = soup.find('span', class_="next").previous_sibling.previous_sibling.text
    return int(depth)


def find_movies(res):
    soup = bs4.BeautifulSoup(res.text, "html.parser")

    # 电影名
    movies = []
    targets = soup.find_all("div", class_="hd")
    for each in targets:
        movies.append(each.a.span.text)

    # 评分
    ranks = []
    targets = soup.find_all("span", class_="rating_num")
    for each in targets:
        ranks.append("评分：%s"% each.text)

    # 资料
    messages = []
    targets = soup.find_all("div", class_="bd")
    for each in targets:
        try:
            messages.append(each.p.text.split('\n')[1].strip() + each.p.text.split('\n')[2].strip())
        except:
            continue

    result = []
    length = len(movies)
    for i in range(length):
        result.append(movies[i] + ranks[i] + messages[i] + '\n')
    return result


def main():
    host = "https://movie.douban.com/top250"
    res = open_url(host)  # 打开主页
    depth = find_depth(res)  # 获取总共的页数

    result = []
    for i in range(depth):
        url = host + "/?start=" + str(25*i)
        res = open_url(url)  # 打开每一页
        result.extend(find_movies(res))  # 将每一页的信息提取出来

    with open("豆瓣电影TOP250.txt", "w", encoding="utf-8") as f:
        for each in result:
            f.write(each)


if __name__ == "__main__":
    main()