day03 爬虫

import requests

response = requests.get(url='http://www.baidu.com/')
response.encoding = 'utf-8'
print(response.text)
with open('baidu.html', 'w', encoding='utf-8') as f:
    f.write(response.text)

response = requests.get('https://video.pearvideo.com/mp4/adshort/20190625/cont-1570302-14057031_adpkg-ad_hd.mp4')
print(response.content)
with open('视频.mp4', 'wb') as f:
    f.write(response.content)

import re

response = requests.get('https://www.pearvideo.com/')
print(response.text)
res_list = re.findall('<a href="video_(.*?)"', response.text, re.S)
print(res_list)

for v_id in res_list:
    detail_url = 'https://www.pearvideo.com/video_' + v_id
    response = requests.get(url=detail_url)
    video_url = re.findall('srcUrl="(.*?)"', response.text, re.S)[0]
    print(video_url)

    video_name = re.findall('<h1 class="video-tt">(.*?)</h1>', response.text, re.S)[0]
    print(video_name)

    v_response = requests.get(video_url)
    with open('%s.mp4' % video_name, 'wb') as f:
        f.write(v_response.content)
        print(video_name, '爬取成功')

import requests
import re


def get_page(base_url):
    response = requests.get(base_url)
    return response


def parse_index(text):
    res = re.findall(
        '<div class="item">.*?<em class="">(.*?)</em>.*?<a href="(.*?)">.*?<span class="title">(.*?)</span>.*?导演:(.*?)</p>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价</span>.*?<span class="inq">(.*?)</span>',
        text, re.S)
    # print(res)
    return res


def save_data(data):
    with open('douban.txt', 'a', encoding='utf-8') as f:
        f.write(data)


if __name__ == '__main__':
    # num = 10
    # base_url = 'https://movie.douban.com/top250?start={}&filter='.format(num)

    num = 0
    for line in range(10):
        base_url = f'https://movie.douban.com/top250?start={num}&filter='
        num += 25
        print(base_url)
        response = get_page(base_url)
        movie_list = parse_index(response.text)
        for movie in movie_list:
            # 电影排名、电影url、电影名称、导演 - 主演 - 类型、电影评分、评价人数、电影简介
            v_top, v_url, v_name, v_daoyan, v_point, v_num, v_desc = movie
            # v_top = movie[0]
            # v_url = movie[1]
            moive_content = f'''
            电影排名: {v_top}
            电影url: {v_url}
            电影名称: {v_name}
            导演主演: {v_daoyan}
            电影评分: {v_point}
            评价人数: {v_num}
            电影简介: {v_desc}
            \n
            '''
            print(moive_content)
            # 保存数据
            save_data(moive_content)