小白通俗版Python爬取b站排行榜top100并编辑为csv文件

import requests
from bs4 import BeautifulSoup
import csv

嘿嘿，该项目需要引入3个库
1.requests（用于连接URL(网络)）
2.bs4（用于解析URL（网络）)
3.csv（把文件保存为csv模式（类似excel））
如果没有这些库可以在dos窗口用‘pip install 库名’来安装

---

1.获取数据所需要的库: requests
2.解析数据所需要的库：beautifulsoup4
3.保存数据到csv的库：csv

1首先第一个库requests用于连接网络

url='https://www.bilibili.com/ranking'
response = requests.get(url)

requests里面的get和post后面加要爬取的网站就可以打开该网站啦
2其次用bs4里面的Beautifulsoup进行网络的解析

html_text=response.text
soup = BeautifulSoup(html_text,'html.parser')

其次用soup的findall来寻找我们要爬取的资料，我以下爬取了6个属性

items = soup.findAll('li', {'class': 'rank-item'})
print(len(items))
for itm in items:
    title = itm.find('a', {'class': 'title'}).text
    up = itm.find_all('a')[2].text
    score = itm.find('div', {'class': 'pts'}).find('div').text
    rank = itm.find('div', {'class': 'num'}).text
    url = itm.find('a', {'class': 'title'}).get('href')
    space = itm.find_all('a')[2].get('href')
    up_id = space[len('//space.bilibili.com/'):]

3最后就是把资料保存下来了
1.定义类保存

class top:
    def __init__(self, rank, title, score, up, up_id, url):
        self.rank = rank
        self.title = title
        self.score = score
        self.up = up
        self.up_id = up_id
        self.url = url

2.定义链表保存数据

topcontent = []

3.完善类，让它可以保存完整数据

class top:
    def __init__(self, rank, title, score, up, up_id, url):
        self.rank = rank
        self.title = title
        self.score = score
        self.up = up
        self.up_id = up_id
        self.url = url

    def tocsv(self):
        return [self.rank, self.title, self.score, self.up, self.up_id, self.url]

    @staticmethod
    def csvtitle():
        return ['rank', 'title', 'score', 'up', 'up_id', 'url']

4.存入类的变量

for itm in items:
    title = itm.find('a', {'class': 'title'}).text
    up = itm.find_all('a')[2].text
    score = itm.find('div', {'class': 'pts'}).find('div').text
    rank = itm.find('div', {'class': 'num'}).text
    url = itm.find('a', {'class': 'title'}).get('href')
    space = itm.find_all('a')[2].get('href')
    up_id = space[len('//space.bilibili.com/'):]

    v = top(rank, title, score, up, up_id, url)
    topcontent.append(v)

5.最后保存到csv就欧克拉

file_name = 'TOP100.csv'
with open(file_name, 'w', newline='', encoding='utf-8') as file:
    pen = csv.writer(file)
    pen.writerow(v.csvtitle())
    for v in topcontent:
        pen.writerow(v.tocsv())

最后附上全代码哈

import requests
from bs4 import BeautifulSoup
import csv


class top:
    def __init__(self, rank, title, score, up, up_id, url):
        self.rank = rank
        self.title = title
        self.score = score
        self.up = up
        self.up_id = up_id
        self.url = url

    def tocsv(self):
        return [self.rank, self.title, self.score, self.up, self.up_id, self.url]

    @staticmethod
    def csvtitle():
        return ['rank', 'title', 'score', 'up', 'up_id', 'url']


url='https://www.bilibili.com/ranking'
response = requests.get(url)
print(requests.get(url))
html_text=response.text
soup = BeautifulSoup(html_text,'html.parser')

topcontent = []

items = soup.findAll('li', {'class': 'rank-item'})
print(len(items))
for itm in items:
    title = itm.find('a', {'class': 'title'}).text
    up = itm.find_all('a')[2].text
    score = itm.find('div', {'class': 'pts'}).find('div').text
    rank = itm.find('div', {'class': 'num'}).text
    url = itm.find('a', {'class': 'title'}).get('href')
    space = itm.find_all('a')[2].get('href')
    up_id = space[len('//space.bilibili.com/'):]

    v = top(rank, title, score, up, up_id, url)
    topcontent.append(v)
print(len(topcontent))

file_name = 'TOP100.csv'
with open(file_name, 'w', newline='', encoding='utf-8') as file:
    pen = csv.writer(file)
    pen.writerow(v.csvtitle())
    for v in topcontent:
        pen.writerow(v.tocsv())