python爬取某乎热榜Top50

小狐狸梦想去童话镇

已于 2024-03-11 09:58:35 修改

阅读量1.2k

点赞数 7

CC 4.0 BY-SA版权

分类专栏： python爬虫文章标签： python 正则表达式 sqlite 数据分析

于 2021-03-22 20:46:49 首次发布

本文链接：https://blog.csdn.net/gets_s/article/details/115096619

python爬虫专栏收录该内容

15 篇文章

订阅专栏

该博客展示了如何使用Python爬虫技术抓取知乎热榜的前50名问题，包括问题链接、排名、标题、简介、评分和配图，并将数据存储到SQLite数据库中。通过正则表达式解析HTML页面，然后利用BeautifulSoup进行数据提取，最后进行数据持久化。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

1、导入第三方库

import urllib.request,urllib.error  #请求网页
from bs4 import BeautifulSoup  # 解析数据
import sqlite3  # 导入数据库
import re # 正则表达式
import time # 获取当前时间

2、程序的主函数

def main():
    # 声明爬取网页
    baseurl = "https://www.zhihu.com/hot"
    # 爬取网页
    datalist = getData(baseurl)
    #保存数据
    dbname = time.strftime("%Y-%m-%d", time.localtime()) # 
    dbpath = "zhihuTop50  " + dbname
    saveData(datalist,dbpath)

3、正则表达式匹配数据

#正则表达式
findlink = re.compile(r'<a class="css-hi1lih" href="(.*?)"') #问题链接
findid = re.compile(r'<div class="css-blkmyu">(.*?)</div>') #问题排名
findtitle = re.compile(r'<h1 class="css-3yucnr">(.*?)</h1>') #问题标题
findintroduce = re.compile(r'<div class="css-1o6sw4j">(.*?)</div>') #简要介绍
findscore = re.compile(r'<div class="css-1iqwfle">(.*?)</div>') #热门评分
findimg = re.compile(r'<img class="css-uw6cz9" src="(.*?)"/>') #文章配图

4、程序运行结果

在这里插入图片描述

5、程序源代码

import urllib.request,urllib.error
from bs4 import BeautifulSoup
import sqlite3
import re
import time

def main():
    # 声明爬取网页
    baseurl = "https://www.zhihu.com/hot"
    # 爬取网页
    datalist = getData(baseurl)
    #保存数据
    dbname = time.strftime("%Y-%m-%d", time.localtime())
    dbpath = "zhihuTop50  " + dbname
    saveData(datalist,dbpath)
    print()
#正则表达式
findlink = re.compile(r'<a class="css-hi1lih" href="(.*?)"') #问题链接
findid = re.compile(r'<div class="css-blkmyu">(.*?)</div>') #问题排名
findtitle = re.compile(r'<h1 class="css-3yucnr">(.*?)</h1>') #问题标题
findintroduce = re.compile(r'<div class="css-1o6sw4j">(.*?)</div>') #简要介绍
findscore = re.compile(r'<div class="css-1iqwfle">(.*?)</div>') #热门评分
findimg = re.compile(r'<img class="css-uw6cz9" src="(.*?)"/>') #文章配图

def getData(baseurl):
    datalist = []
    html = askURL(baseurl)
    # print(html)

    soup = BeautifulSoup(html,'html.parser')
    for item in soup.find_all('a',class_="css-hi1lih"):
        # print(item)
        data = []
        item = str(item)

        Id = re.findall(findid,item)
        if(len(Id) == 0):
            Id = re.findall(r'<div class="css-mm8qdi">(.*?)</div>',item)[0]
        else: Id = Id[0]
        data.append(Id)
        # print(Id)

        Link = re.findall(findlink,item)[0]
        data.append(Link)
        # print(Link)

        Title = re.findall(findtitle,item)[0]
        data.append(Title)
        # print(Title)

        Introduce = re.findall(findintroduce,item)
        if(len(Introduce) == 0):
            Introduce = " "
        else:Introduce = Introduce[0]
        data.append(Introduce)
        # print(Introduce)

        Score = re.findall(findscore,item)[0]
        data.append(Score)
        # print(Score)

        Img = re.findall(findimg,item)
        if (len(Img) == 0):
            Img = " "
        else: Img = Img[0]
        data.append(Img)
        # print(Img)
        datalist.append(data)
    return datalist
def askURL(baseurl):
    # 设置请求头
    head = {
        # "User-Agent": "Mozilla/5.0 (Windows NT 10.0;Win64;x64) AppleWebKit/537.36(KHTML, likeGecko) Chrome/80.0.3987.163Safari/537.36"
        "User-Agent": "Mozilla / 5.0(iPhone;CPUiPhoneOS13_2_3likeMacOSX) AppleWebKit / 605.1.15(KHTML, likeGecko) Version / 13.0.3Mobile / 15E148Safari / 604.1"
    }
    request = urllib.request.Request(baseurl, headers=head)
    html = ""
    try:
        response = urllib.request.urlopen(request)
        html = response.read().decode("utf-8")
        # print(html)
    except urllib.error.URLError as e:
        if hasattr(e, "code"):
            print(e.code)
        if hasattr(e, "reason"):
            print(e.reason)
    return html
    print()
def saveData(datalist,dbpath):
    init_db(dbpath)
    conn = sqlite3.connect(dbpath)
    cur = conn.cursor()

    for data in datalist:
        sql = '''
        insert into Top50(
        id,info_link,title,introduce,score,img)
        values("%s","%s","%s","%s","%s","%s")'''%(data[0],data[1],data[2],data[3],data[4],data[5])
        print(sql)
        cur.execute(sql)
        conn.commit()
    cur.close()
    conn.close()
def init_db(dbpath):
    sql = '''
    create table Top50
    (
    id integer primary key autoincrement,
    info_link text,
    title text,
    introduce text,
    score text,
    img text
    )
    '''
    conn = sqlite3.connect(dbpath)
    cursor = conn.cursor()
    cursor.execute(sql)
    conn.commit()
    conn.close()

if __name__ =="__main__":
    main()