源码

import urllib.request
import urllib.error
from bs4 import BeautifulSoup
import re


def askurl(url):
    head = {  # 模拟浏览器头部信息，这段我抄的https://blog.csdn.net/bookssea/article/details/107309591
        "User-Agent": "Mozilla / 5.0(Windows NT 10.0; Win64; x64) AppleWebKit / 537.36(KHTML, like Gecko) Chrome / 80.0.3987.122  Safari / 537.36"
    }

    request = urllib.request.Request(url, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
    except urllib.error.URLError as e:
        if hasattr(e, "code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)

    #    print("URL内容请求成功")
    return html


def get_page():
    #    取前10页
    urls = ['https://bgm.tv/anime/browser?sort=rank&page={}'.format(str(i)) for i in range(1, 277)]
    #    输出验证
    #    print(urls)
    return urls


def clearblankline():
    global i
    with open('1.txt', 'r', encoding='utf-8') as fr, open('bgm排行榜.txt', 'w', encoding='utf-8') as fd:
        for text in fr.readlines():
            if text.split():
                fd.write(text)
                i += 1
                if i % 4 == 0:
                    fd.write('\n')
        print('输出成功....')


def show():
    global a
    print(a)
    a += 1


if __name__ == "__main__":
    a = 1
    i = 0
    for url in get_page():
        html = askurl(url)  # 保存获取到的网页源码
        bs = BeautifulSoup(html, 'html.parser')

        for name in bs.find_all('li', class_=re.compile('(item )(odd|even)( clearit)')):
            # print(name.get_text())
            txtfile = open("1.txt", 'a', encoding='utf-8')
            txtfile.write(name.get_text())
            txtfile.close()
            show()
    print("爬取完成")
    clearblankline()

分析源码

askurl()函数

请求网页源码，因为是照搬了网上找到的一段代码，就不多做分析，直接使用即可。

get_page()函数

功能：获取多个页面

clearblankline()函数

功能：打开源文件清除空行并以每4行一空行的格式输出新文件

split()判断该行是否有内容，如果有内容则值为真，而fd.write()用来写入源文本，每4行插入换行符“\n”

show()函数

功能：显示进程速度

主函数

bs.find_all('li', class_=re.compile('(item )(odd|even)( clearit)'))

使用了正则表达式来进行查找

附源码地址：

https://github.com/zero617/Crawler_Learning/tree/main/bgm