Python爬虫收集今日热榜数据：聚合全网热点排行榜

 pip install websocket-client

废话不多说数据展示：

代码：

创建工作簿和工作表

# 创建工作簿和工作表
workbook = openpyxl.Workbook()
sheet = workbook.active
sheet.title = '实时热榜'

设置标题行

titles = ["序号", "平台", "热榜描述", "热度", "访问地址"]
for col, title in enumerate(titles, 1):
    sheet.cell(row=1, column=col).value = title

数据获取核心代码：

def get_html(url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'}
    resp = requests.get(url, headers=headers)
    return resp.text


def get_data(html):
    soup = BeautifulSoup(html, 'html.parser')
    nodes = soup.find_all('div', class_='cc-cd')
    return nodes


url = 'https://tophub.today'
html = get_html(url)
data = get_data(html)

将数据保存到xlsx

for node in data:
    source = node.find('div', class_='cc-cd-lb').text.strip()
    print(source)
    if source == '实时榜中榜':
        # 终止循环
        continue

    messages = node.find('div', class_='cc-cd-cb-l nano-content').find_all('a')
    print(messages)
    for message in messages:
        rank = message.find('span', class_='s').text.strip()
        content = message.find('span', class_='t').text.strip()
        content1 = message.find('span', class_='e').text.strip()
        url = message["href"]
        sheet.append([rank, source,  content,  content1, url])


# 保存数据到Excel文件
workbook.save('hot.xlsx')
workbook.close()

完整code：

import requests
from bs4 import BeautifulSoup
import openpyxl

# 创建工作簿和工作表
workbook = openpyxl.Workbook()
sheet = workbook.active
sheet.title = '实时热榜'

# 设置标题行
titles = ["序号", "平台", "热榜描述", "热度", "访问地址"]
for col, title in enumerate(titles, 1):
    sheet.cell(row=1, column=col).value = title

def get_html(url):
    headers = {
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.132 Safari/537.36'}
    resp = requests.get(url, headers=headers)
    return resp.text


def get_data(html):
    soup = BeautifulSoup(html, 'html.parser')
    nodes = soup.find_all('div', class_='cc-cd')
    return nodes


url = 'https://tophub.today'
html = get_html(url)
data = get_data(html)
# print(data)

for node in data:
    source = node.find('div', class_='cc-cd-lb').text.strip()
    print(source)
    if source == '实时榜中榜':
        # 终止循环
        continue

    messages = node.find('div', class_='cc-cd-cb-l nano-content').find_all('a')
    print(messages)
    for message in messages:
        rank = message.find('span', class_='s').text.strip()
        content = message.find('span', class_='t').text.strip()
        content1 = message.find('span', class_='e').text.strip()
        url = message["href"]
        sheet.append([rank, source,  content,  content1, url])


# 保存数据到Excel文件
workbook.save('hot.xlsx')
workbook.close()

关注公众号「码农园区」，获取多个项目源码及各大厂学习面试资源