爬虫学习3：爬虫的深度爬取

news2024/9/24 7:19:00

爬虫的深度爬取和爬取视频的方式

深度爬取豆瓣读书

import time
import fake_useragent
import requests
from lxml import etree
head = {
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36 Edg/126.0.0.0"
}
if __name__ == '__main__':
    # 1、url
    url = "https://book.douban.com/tag/%E4%BA%92%E8%81%94%E7%BD%91"#url地址
    # 2、发送请求
    resp = requests.get(url, headers=head)
    time.sleep(5)
    # 3、获取想要的数据
    res_text = resp.text#获得html形式的数据
    # 4、数据解析
    tree = etree.HTML(res_text)#将html转化为元素形式
    a_list = tree.xpath("//ul[@class='subject-list']/li/div[2]/h2/a")
    for a in a_list:
        time.sleep(3)
        # 1、url
        book_url = "".join(a.xpath("./@href"))#里面的网页的url
        # 2、发送请求
        book_res = requests.get(book_url, headers=head)
        # 3、获取想要的信息
        book_text = book_res.text
        # 4、数据解析
        book_tree = etree.HTML(book_text)
        book_name = "".join(book_tree.xpath("//span[@property='v:itemreviewed']/text()"))
        author = "".join(book_tree.xpath("//div[@class='subject clearfix']/div[2]/span[1]/a/text()"))
        publish = "".join(book_tree.xpath("//div[@class='subject clearfix']/div[2]/a[1]/text()"))
        y = "".join(book_tree.xpath("//span[@class='pl' and text()='出版年:']/following-sibling::text()[1]"))
        page = "".join(book_tree.xpath("//span[@class='pl' and text()='页数:']/following-sibling::text()[1]"))
        price = "".join(book_tree.xpath("//span[@class='pl' and text()='定价:']/following-sibling::text()[1]"))
        bind = "".join(book_tree.xpath("//span[@class='pl' and text()='装帧:']/following-sibling::text()[1]"))
        isbn = "".join(book_tree.xpath("//span[@class='pl' and text()='ISBN:']/following-sibling::text()[1]"))
        print(book_name, author, publish, y, page, price, bind, isbn)
    pass

代码思路

![在这里插入图片描述](https://i-blog.csdnimg.cn/direct/1769d142fe7f40c1b401416884ba93ec.jpeg#pic_center

B站爬取视频

# requests 请求b站视频
import json
import fake_useragent
import requests
from lxml import etree
if __name__ == '__main__':
    # UA伪装
    head = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36 Edg/126.0.0.0"
        # 防盗链
        , "Referer": "https://www.bilibili.com/"#必须有
        ,
        "Cookie": "这里是登录要求，输入个人的登录信息"
    }
    # 1、指定url
    url = "https://www.bilibili.com/video/BV12z421z75d/?spm_id_from=333.1007.tianma.2-1-4.click&vd_source=4b1ef23e5d47e143cfb702705740719d"
    # 2、发送请求
    response = requests.get(url, headers=head)
    # 3、获取响应的数据
    res_text = response.text
    # 4、数据解析
    tree = etree.HTML(res_text)
    with open("b.html", "w", encoding="utf8") as f:
        f.write(res_text)
    base_info = "".join(tree.xpath("/html/head/script[4]/text()"))[20:]#b站固定的位置html/head/script[4]，前面的不需要，只有括号里的字符串有用所有取20以后的
    info_dict = json.loads(base_info)
    video_url = info_dict["data"]["dash"]['video'][0]["baseUrl"]#视频
    audio_url = info_dict["data"]["dash"]['audio'][0]["baseUrl"]#音频
    video_content = requests.get(video_url, head).content#和图片一样采用content
    audio_content = requests.get(audio_url, head).content
    with open("video.wmv", "wb") as f:#以二进制的形式
        f.write(video_content)
    with open("audio.mp4", "wb") as fp:
        fp.write(audio_content)

    pass