Python爬取 分析Ajax爬取B站python视频---详细资料

Flag:一天一爬虫。

这篇是转的:https://blog.csdn.net/sixkery/article/details/81946308

亲测有效,

对转载网站的分析做进一步分析补充:

分析页面:

如何获取api?

这次我直接打开开发者工具，切换到Network下查找api，要点击Python旁边的搜索按钮，不然Network一片空白,

 点击搜索之后：

 会在其中找到，一个以api开头的网址，但是我们不能用此url作为我们爬取的对象，因为此url，没有包含page={},无法多页爬取,

此url只搜集这一页的视频信息。

此url

https://api.bilibili.com/x/web-interface/search/all?jsonp=jsonp&highlight=1&keyword=python&callback=__jp0

 然后，

 依次点击尝试，

找到page，意味着可以多页爬取了,然后就是构造url。

代码:

import requests
import json, re, time
from requests.exceptions import RequestException


class Spider():

    def get_page(self, page):
        try:
            headers = {
                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64)'
                              ' AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
            }
            url = 'https://api.bilibili.com/x/web-interface/search/type?jsonp=jsonp&&search_type=video&highlight=1&keyword=python&page={}'.format(
                page)
            r = requests.get(url, headers)
            if r.status_code == 200:
                return r.text
            else:
                print(r.status_code)
        except RequestException:
            print('请求失败')
            return None

    def parse_page(self, html):
        # 转换成JSON对象，好操作
        data = json.loads(html)

        results = data.get('data').get('result')
        for result in results:
            # 获取图片地址
            image_url = result['pic']
            # 获取视频地址
            video_url = result['arcurl']
            # 获取作者
            video_author = result['author']
            # 获取视频标题，中间有额外的字符，用re替换一下
            video_title = result['title']
            video_title = re.sub('[Pp]ython', 'Python', video_title)
            # 获取播放量
            video_play = result['play']
            # 获取上传时间,这里将时间戳转换成标准格式
            video_date = result['pubdate']
            timestr = time.localtime(video_date)
            video_date = time.strftime('%Y-%m-%d %H-%M-%S', timestr)
            print(image_url, video_url, video_title, video_play, video_date)

    def run(self):#爬取前三页
        for i in range(1, 3):
            html = self.get_page(i)
            self.parse_page(html)


def main():
    spider = Spider()
    spider.run()


if __name__ == '__main__':
    main()

爬取结果,

本来想爬一下那个all的api，奈何能力不够，找代理池，换header都解决不了问题，，

此处先贴上代码，以后解决。

import requests
import json, re, time
from requests.exceptions import RequestException
import random
import urllib as ulb
class Spider():

    def get_page(self):
        try:
            my_headers = [
                "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
                "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36",
                "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:30.0) Gecko/20100101 Firefox/30.0",
                "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_2) AppleWebKit/537.75.14 (KHTML, like Gecko) Version/7.0.3 Safari/537.75.14",
                "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.2; Win64; x64; Trident/6.0)",
                'Mozilla/5.0 (Windows; U; Windows NT 5.1; it; rv:1.8.1.11) Gecko/20071127 Firefox/2.0.0.11',
                'Opera/9.25 (Windows NT 5.1; U; en)',
                'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)',
                'Mozilla/5.0 (compatible; Konqueror/3.5; Linux) KHTML/3.5.5 (like Gecko) (Kubuntu)',
                'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.0.12) Gecko/20070731 Ubuntu/dapper-security Firefox/1.5.0.12',
                'Lynx/2.8.5rel.1 libwww-FM/2.14 SSL-MM/1.4.1 GNUTLS/1.2.9',
                "Mozilla/5.0 (X11; Linux i686) AppleWebKit/535.7 (KHTML, like Gecko) Ubuntu/11.04 Chromium/16.0.912.77 Chrome/16.0.912.77 Safari/535.7",
                "Mozilla/5.0 (X11; Ubuntu; Linux i686; rv:10.0) Gecko/20100101 Firefox/10.0 "
            ]
            headers =random.choice(my_headers)
            url = 'https://api.bilibili.com/x/web-interface/search/all?jsonp=jsonp&highlight=1&keyword=python&callback=__jp0'
            proxies = {
                'https': 'https://114.99.7.122:8752'}
            proxy_list = [
                '183.95.80.102:8080',
                '123.160.31.71:8080',
                '115.231.128.79:8080',
                '166.111.77.32:80',
                '43.240.138.31:8080',
                '218.201.98.196:3128'
            ]
            # 随机从IP列表中选择一个IP
            proxy = random.choice(proxy_list)
            # 基于选择的IP构建连接
            urlhandle = ulb.request.ProxyHandler({'http': proxy})
            opener = ulb.request.build_opener(urlhandle)
            ulb.request.install_opener(opener)

            r = requests.get(url, headers,proxies=proxies)
            if r.status_code == 200:
                return r.text
            else:
                print(r.status_code)
        except RequestException:
            print('请求失败')
            return None

    def parse_page(self, html):
        print(html)
        # 转换成JSON对象，好操作
        # data = json.loads(html)
        # print(data)
#        results = data.get('data').get('result')
#         results=data.get('data').get('result').get('video')
#         for result in results:
#             author_=result['author']
#             print(author_)
            # # 获取图片地址
            # image_url = result['pic']
            # # 获取视频地址
            # video_url = result['arcurl']
            # # 获取作者
            # video_author = result['author']
            # # 获取视频标题，中间有额外的字符，用re替换一下
            # video_title = result['title']
            # video_title = re.sub('[Pp]ython', 'Python', video_title)
            # # 获取播放量
            # video_play = result['play']
            # # 获取上传时间,这里将时间戳转换成标准格式
            # video_date = result['pubdate']
            # timestr = time.localtime(video_date)
            # video_date = time.strftime('%Y-%m-%d %H-%M-%S', timestr)
            # print(image_url, video_url, video_title, video_play, video_date)

    def run(self):#爬取前三页
        html = self.get_page()
        self.parse_page(html)
        # for i in range(1, 3):
        #     html = self.get_page(i)
        #     self.parse_page(html)


def main():
    spider = Spider()
    spider.run()


if __name__ == '__main__':
    main()