Python 学习day4

知识回顾:
    爬虫原理:
        什么是爬虫？
            爬虫指的是爬取数据。

        什么是互联网？
            由一堆网络设备把一台一台的计算机互联到一起。

        互联网建立的目的？
            数据的传递与数据的共享。

        上网的全过程:
            - 普通用户
                打开浏览器 --> 往目标站点发送请求 --> 接收响应数据 --> 渲染到页面上。

            - 爬虫程序
                模拟浏览器 --> 往目标站点发送请求 --> 接收响应数据 --> 提取有用的数据 --> 保存到本地/数据库。

        浏览器发送的是什么请求？
            http协议的请求:
                - 请求url
                - 请求方式:
                    GET、POST

                - 请求头:
                    cookies
                    user-agent
                    host

        爬虫的全过程:
            1、发送请求 （请求库）
                - requests模块
                - selenium模块

            2、获取响应数据（服务器返回）

            3、解析并提取数据（解析库）
                - re正则
                - bs4（BeautifulSoup4）
                - Xpath

            4、保存数据（存储库）
                - MongoDB

            1、3、4需要手动写。

            - 爬虫框架
                Scrapy（基于面向对象）

        爬取梨视频:
            1、分析网站的视频源地址
            2、通过requests网视频源地址发送请求
            3、获取视频的二进制流，并保存到本地。

        使用Chrome浏览器工具
            打开开发者模式 ----> network ---> preserve log、disable cache

今日内容:
    requests模块详细使用
    //selenium模块
　　 高级爬虫

一.爬取梨视频（当前页面全部）

'''
爬取梨视频:
请求url:
    https://www.pearvideo.com/
    
请求方式:
    GET
    
请求头:
    user-agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36
'''

# import requests
# import re  # 正则模块
#
# # 1、对梨视频详情页发送请求，获取响应数据
# response = requests.get(url='https://www.pearvideo.com/')
# print(response.status_code)
# print(response.text)
#
# # re.findall('正则匹配规则', '解析文本', "正则模式")
# # re.S: 全局模式 （对整个文本行进匹配）
# # .指的是当前位置
# # *指的是查找所有
# '''
# <a href="video_1543373"
# <a href="video_(.*?)"  # 提取1543373
# '''
#
# # 2、获取主页视频详情页ID
# res = re.findall('<a href="video_(.*?)"', response.text, re.S)
# print(res)
#
#
# for m_id in res:
#     # 拼接详情页url
#     detail_url = 'https://www.pearvideo.com/video_' + m_id
#     print(detail_url)



import requests
import re  # 正则模块
# uuid.uuid4()  可以根据时间戳生成一段世界上唯一的随机字符串
import uuid

# 爬虫三部曲

# 1、发送请求
def get_page(url):
    response = requests.get(url)
    return response

# 2、解析数据
# 解析主页获取视频详情页ID
def parse_index(text):
    res = re.findall('<a href="video_(.*?)"', text, re.S)
    # print(res)

    detail_url_list = []
    for m_id in res:
        # 拼接详情页url
        detail_url = 'https://www.pearvideo.com/video_' + m_id
        # print(detail_url)
        detail_url_list.append(detail_url)

    # print(detail_url_list)

    return detail_url_list

# 解析详情页获取视频url
def parse_detail(text):
    ''''''
    '''
        (.*?)： 提取括号的内容
        .*?： 直接匹配
        <video webkit-playsinline="" playsinline="" x-webkit-airplay="" autoplay="autoplay" src="https://video.pearvideo.com/mp4/adshort/20190613/cont-1566073-14015522_adpkg-ad_hd.mp4" style="width: 100%; height: 100%;"></video>
        
    正则: <video.*?src="(.*?)"
    
    # 以上是分析过程，不需要写
    
    正则: srcUrl="(.*?)"
    '''
    movie_url = re.findall('srcUrl="(.*?)"', text, re.S)[0]
    return movie_url


# 3、保存数据
def save_movie(movie_url):
    response = requests.get(movie_url)
    # 把视频写到本地
    with open(f'{uuid.uuid4()}.mp4', 'wb') as f:
        f.write(response.content)
        f.flush()

if __name__ == '__main__':  # main + 回车键

    # 1、对主页发送请求
    index_res = get_page(url='https://www.pearvideo.com/')

    # 2、对主页进行解析、获取详情页id
    detail_url_list = parse_index(index_res.text)
    # print(detail_url_list)

    # 3、对每个详情页url发送请求
    for detail_url in detail_url_list:
        detail_res = get_page(url=detail_url)
        print(detail_res.text)

        # 4、解析详情页获取视频url
        movie_url = parse_detail(detail_res.text)
        print(movie_url)

        # 5、保存视频
        save_movie(movie_url)

二.requests.get详解
（绕过知乎登录页面）
（访问ahpu百度百科）
（gethub数据查询）

'''
GET请求讲解
'''
'''
User-Agent
# 访问知乎发现
请求url:
    https://www.zhihu.com/explore
    
请求方式:
    GET
    
请求头:
    user-agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36
    
    cookies
'''

# 访问知乎
# import requests
# response = requests.get(url='https://www.zhihu.com/explore')
# print(response.status_code)  # 400
# print(response.text)  # 返回错误页面


# 携带请求头参数访问知乎:
import requests

# 请求头字典
# headers = {
#     'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
# }
# 在get请求内，添加user-agent
# response = requests.get(url='https://www.zhihu.com/explore', headers=headers)
# print(response.status_code)  # 200
# # print(response.text)
# with open('zhihu.html', 'w', encoding='utf-8') as f:
#     f.write(response.text)


'''
params请求参数
访问百度搜查安徽工程大学url
https://www.baidu.com/s?wd=安徽工程大学&pn=10
https://www.baidu.com/s?wd=安徽工程大学&pn=20

# '''
from urllib.parse import urlencode
# url = 'https://www.baidu.com/s?wd=%E8%94%A1%E5%BE%90%E5%9D%A4'
# url = 'https://www.baidu.com/s?' + urlencode({"wd": "蔡徐坤"})
url = 'https://www.baidu.com/s?'
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
}
# print(url)
# 在get方法中添加params参数
# response = requests.get(url, headers=headers, params={"wd": "安徽工程大学"})
response = requests.get(url, headers=headers, params={"wd": "安徽工程大学", "pn": "20"})
# print(response.text)
with open('gongcheng2.html', 'w', encoding='utf-8') as f:
    f.write(response.text)


'''
携带cookies
携带登录cookies破解github登录验证

请求url:
    https://github.com/settings/emails
    
请求方式:
    GET
    
请求头:
    User-Agen
    
    Cookie: has_recent_activity=1; _ga=GA1.2.1416117396.1560496852; _gat=1; tz=Asia%2FShanghai; _octo=GH1.1.1728573677.1560496856; _device_id=1cb66c9a9599576a3b46df2455810999; user_session=1V8n9QfKpbgB-DhS4A7l3Tb3jryARZZ02NDdut3J2hy-8scm; __Host-user_session_same_site=1V8n9QfKpbgB-DhS4A7l3Tb3jryARZZ02NDdut3J2hy-8scm; logged_in=yes; dotcom_user=TankJam; _gh_sess=ZS83eUYyVkpCWUZab21lN29aRHJTUzgvWjRjc2NCL1ZaMHRsdGdJeVFQM20zRDdPblJ1cnZPRFJjclZKNkcrNXVKbTRmZ3pzZzRxRFExcUozQWV4ZG9kOUQzZzMwMzA2RGx5V2dSaTMwaEZ2ZDlHQ0NzTTBtdGtlT2tVajg0c0hYRk5IOU5FelYxanY4T1UvVS9uV0YzWmF0a083MVVYVGlOSy9Edkt0aXhQTmpYRnVqdFAwSFZHVHZQL0ZyQyt0ZjROajZBclY4WmlGQnNBNTJpeEttb3RjVG1mM0JESFhJRXF5M2IwSlpHb1Mzekc5M0d3OFVIdGpJaHg3azk2aStEcUhPaGpEd2RyMDN3K2pETmZQQ1FtNGNzYnVNckR4aWtibkxBRC8vaGM9LS1zTXlDSmFnQkFkWjFjanJxNlhCdnRRPT0%3D--04f6f3172b5d01244670fc8980c2591d83864f60
    
'''
import requests

# 请求url
url = 'https://github.com/settings/emails'

# 请求头
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36',
    # 在请求头中拼接cookies
    # 'Cookie': 'has_recent_activity=1; _ga=GA1.2.1416117396.1560496852; _gat=1; tz=Asia%2FShanghai; _octo=GH1.1.1728573677.1560496856; _device_id=1cb66c9a9599576a3b46df2455810999; user_session=1V8n9QfKpbgB-DhS4A7l3Tb3jryARZZ02NDdut3J2hy-8scm; __Host-user_session_same_site=1V8n9QfKpbgB-DhS4A7l3Tb3jryARZZ02NDdut3J2hy-8scm; logged_in=yes; dotcom_user=TankJam; _gh_sess=ZS83eUYyVkpCWUZab21lN29aRHJTUzgvWjRjc2NCL1ZaMHRsdGdJeVFQM20zRDdPblJ1cnZPRFJjclZKNkcrNXVKbTRmZ3pzZzRxRFExcUozQWV4ZG9kOUQzZzMwMzA2RGx5V2dSaTMwaEZ2ZDlHQ0NzTTBtdGtlT2tVajg0c0hYRk5IOU5FelYxanY4T1UvVS9uV0YzWmF0a083MVVYVGlOSy9Edkt0aXhQTmpYRnVqdFAwSFZHVHZQL0ZyQyt0ZjROajZBclY4WmlGQnNBNTJpeEttb3RjVG1mM0JESFhJRXF5M2IwSlpHb1Mzekc5M0d3OFVIdGpJaHg3azk2aStEcUhPaGpEd2RyMDN3K2pETmZQQ1FtNGNzYnVNckR4aWtibkxBRC8vaGM9LS1zTXlDSmFnQkFkWjFjanJxNlhCdnRRPT0%3D--04f6f3172b5d01244670fc8980c2591d83864f60'
}
# github_res = requests.get(url, headers=headers)

import requests
cookies = {
    'Cookie': 'has_recent_activity=1; _ga=GA1.2.1416117396.1560496852; _gat=1; tz=Asia%2FShanghai; _octo=GH1.1.1728573677.1560496856; _device_id=1cb66c9a9599576a3b46df2455810999; user_session=1V8n9QfKpbgB-DhS4A7l3Tb3jryARZZ02NDdut3J2hy-8scm; __Host-user_session_same_site=1V8n9QfKpbgB-DhS4A7l3Tb3jryARZZ02NDdut3J2hy-8scm; logged_in=yes; dotcom_user=TankJam; _gh_sess=ZS83eUYyVkpCWUZab21lN29aRHJTUzgvWjRjc2NCL1ZaMHRsdGdJeVFQM20zRDdPblJ1cnZPRFJjclZKNkcrNXVKbTRmZ3pzZzRxRFExcUozQWV4ZG9kOUQzZzMwMzA2RGx5V2dSaTMwaEZ2ZDlHQ0NzTTBtdGtlT2tVajg0c0hYRk5IOU5FelYxanY4T1UvVS9uV0YzWmF0a083MVVYVGlOSy9Edkt0aXhQTmpYRnVqdFAwSFZHVHZQL0ZyQyt0ZjROajZBclY4WmlGQnNBNTJpeEttb3RjVG1mM0JESFhJRXF5M2IwSlpHb1Mzekc5M0d3OFVIdGpJaHg3azk2aStEcUhPaGpEd2RyMDN3K2pETmZQQ1FtNGNzYnVNckR4aWtibkxBRC8vaGM9LS1zTXlDSmFnQkFkWjFjanJxNlhCdnRRPT0%3D--04f6f3172b5d01244670fc8980c2591d83864f60'
}

github_res = requests.get(url, headers=headers, cookies=cookies)

print('15622792660' in github_res.text)

三、爬虫升级（爬取豆瓣250部视频相关信息）

''''''
'''
主页:
    https://movie.douban.com/top250
    GET
    User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36
    
re正则:
    # 电影详情页url、图片链接、电影名称、电影评分、评价人数
    <div class="item">.*?href="(.*?)">.*?src="(.*?)".*?<span class="title">(.*?)</span>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价
'''
import requests
import re
count = 0
flag = 1
while flag
    _id = 'count'
    url = 'https://movie.douban.com/top250?=' + _id
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36'
    }
    # 1、往豆瓣TOP250发送请求获取响应数据
    response = requests.get(url, headers=headers)
    
    # print(response.text)
    
    # 2、通过正则解析提取数据
    # 电影详情页url、图片链接、电影名称、电影评分、评价人数
    movie_content_list = re.findall(
        # 正则规则
        '<div class="item">.*?href="(.*?)">.*?src="(.*?)".*?<span class="title">(.*?)</span>.*?<span class="rating_num".*?>(.*?)</span>.*?<span>(.*?)人评价',
    
        # 解析文本
        response.text,
    
        # 匹配模式
        re.S)
    
    for movie_content in movie_content_list:
        # 解压赋值每一部电影
        detail_url, movie_jpg, name, point, num = movie_content
        data = f'电影名称:{name},   详情页url:{detail_url}, 图片url:{movie_jpg}, 评分: {point}, 评价人数: {num} \n'
        print(data)
    
        # 3、保存数据，把电影信息写入文件中
        with open('douban250.txt', 'a', encoding='utf-8') as f:
            f.write(data)
    count += 225
    if count >225:
        flag =0

猜你喜欢