如何使用python爬取知乎热榜Top50数据
作者:小狐狸梦想去童话镇
主要是爬取知乎热榜的问题及点赞数比较高的答案,通过requests请求库进行爬取,对大家的学习或工作具有一定的价值,需要的朋友可以参考下
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="(.*?)" rel="external nofollow" rel="external nofollow" ') #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
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="(.*?)" rel="external nofollow" rel="external nofollow" ') #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()
到此这篇关于如何使用python爬取知乎热榜Top50数据的文章就介绍到这了,更多相关python 爬取知乎内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家!