利用python爬虫获取中国最好大学排名和B站排行榜视频

笔者刚学到python爬虫 无聊玩一玩

功能描述：

1. 输入url
2. 获取一系列的数据
3. 在命令板输出

技术路线：requests>bs4

步骤：

1. List item
2. 先从网上找到中国大学排名的url中国最好大学
3. 分析其html结构
   
   
4. 利用bs，做出一个list内嵌dict与tuple

import requests
from bs4 import BeautifulSoup


def getContent(url):
    try:
        r = requests.get(url)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "爬取失败"


def makeSoup(content):
    soup = BeautifulSoup(content, "html.parser")
    return soup


def tackleContents(soup): # 由分析html结构得出
    l = [] # 字典list
    l1 = [] # 元组list
    for i in soup.findAll(name="tr", class_="alt"):
        # print(i)
        d = {}
        td_list = i.findAll(name="td")
        d["ranking"] = int(td_list[0].string)
        d["name"] = td_list[1].div.string
        d["location"] = td_list[2].string
        d["type"] = td_list[3].string
        d["score"] = float(td_list[4].string)
        t = (d["ranking"], d["name"], d["location"], d["type"], d["score"])
        l.append(d)
        l1.append(t)
    return l, l1

5. 将列表作为全局量，命令版控制查看

# 字典形式
def selectByName(name):
    result = None
    for r in l:
        if r["name"] == name:
            result = r
            return result
    if result is None:
        return "无结果"


# 元组形式
def selectByNumber(number):
    if 1<=number<=len(l1):
        return l1[number-1]
    else:
        return "无结果"

最后用命令行（无聊形式）…

print("正在网上收取排名结果，请骚等...\n")
l, l1 = tackleContents(makeSoup(getContent("http://www.zuihaodaxue.com/zuihaodaxuepaiming2020.html")))
choice = None
while choice != '0':
    choice = input("请输入您要查看的依据（1.校名、2.排名、0.退出）：")
    if choice == "1":
        c = input("请输入您的校名：")
        print(selectByName(c))
    elif choice=="2":
        n = input("请输入您的排名：")
        print(selectByNumber(int(n)))
    elif choice=="0":
        break
    else:
        print("请输入正确的选项")

6.结果展示

最后附上B站的排行榜（直接上代码）html结构分析可照着以下代码慢慢看就不放html图了

import requests
from bs4 import BeautifulSoup

# b站播放量
def get_content():
    list1 = []
    url = "https://www.bilibili.com/ranking?spm_id_from=333.851.b_7072696d61727950616765546162.3"
    r = requests.get(url)
    r.encoding = "utf-8"
    soup = BeautifulSoup(r.text, "html.parser")
    number = 0
    for p in soup.findAll("div", class_="info"):
        dict1 = {}
        number += 1
        a = p.find("a")
        spans = p.findAll("span", class_="data-box")
        if not spans:
            continue
        if not a:
            continue
        dict1.setdefault("name", a.get_text())
        dict1.setdefault("wow", spans[0].get_text())
        dict1.setdefault("comment", spans[1].get_text())
        dict1.setdefault("link", a["href"])
        list1.append(dict1)
    return list1


for i in get_content():
    print(i)

运行结果

第一次写CSDN，也算是笔记吧哈哈哈哈哈

by Molala