欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

Python网络爬虫03——简单爬虫实例

程序员文章站 2022-05-08 18:26:14
...

代码如下:

author = 'damao'

"""爬虫练习一:爬去迅播影院电影名称"""

from requests_html import HTMLSession


class TestSpiderFilmNames(object):

    def __init__(self):
        self._session = HTMLSession()
        self._url = 'http://www.0597ren.com/'
        self.get_link = self._session.get(self._url)

    @property
    def session(self):
        return self._session

    def get_all_links(self):
        get_link = self.get_link
        for _ in get_link.html.links:
            print(_)

    # 获取首页电影名称
    def __str__(self):  # get_film_names
        respones = self.get_link
        print(respones)
        content = respones.html.find('div.content',first=True)
        list_name = content.find('li')
        # print(content)
        list_film_data = []
        for li in list_name:
            moive_name = li .find('a',first=True).attrs['title']
            print(moive_name)
            list_film_data.append(moive_name)
        print("共获得{a}部电影。".format(a=len(list_film_data)))


if __name__ == '__main__':
    TestSpiderFilmNames().__str__()
    # t.get_all_links()
    # t.get_all_name()
    # t.get_film_names()