如何使用python爬取知乎熱榜Top50數據
1、導入第三方庫
import urllib.request,urllib.error #請求網頁 from bs4 import BeautifulSoup # 解析數據 import sqlite3 # 導入數據庫 import re # 正則表達式 import time # 獲取當前時間
2、程序的主函數
def main(): # 聲明爬取網頁 baseurl = "https://www.zhihu.com/hot" # 爬取網頁 datalist = getData(baseurl) #保存數據 dbname = time.strftime("%Y-%m-%d", time.localtime()) # dbpath = "zhihuTop50 " + dbname saveData(datalist,dbpath)
3、正則表達式匹配數據
#正則表達式 findlink = re.compile(r'<a class="css-hi1lih" href="(.*?)" rel="external nofollow" rel="external nofollow" ') #問題鏈接 findid = re.compile(r'<div class="css-blkmyu">(.*?)</div>') #問題排名 findtitle = re.compile(r'<h1 class="css-3yucnr">(.*?)</h1>') #問題標題 findintroduce = re.compile(r'<div class="css-1o6sw4j">(.*?)</div>') #簡要介紹 findscore = re.compile(r'<div class="css-1iqwfle">(.*?)</div>') #熱門評分 findimg = re.compile(r'<img class="css-uw6cz9" src="(.*?)"/>') #文章配圖
4、程序運行結果
5、程序源代碼
import urllib.request,urllib.error from bs4 import BeautifulSoup import sqlite3 import re import time def main(): # 聲明爬取網頁 baseurl = "https://www.zhihu.com/hot" # 爬取網頁 datalist = getData(baseurl) #保存數據 dbname = time.strftime("%Y-%m-%d", time.localtime()) dbpath = "zhihuTop50 " + dbname saveData(datalist,dbpath) print() #正則表達式 findlink = re.compile(r'<a class="css-hi1lih" href="(.*?)" rel="external nofollow" rel="external nofollow" ') #問題鏈接 findid = re.compile(r'<div class="css-blkmyu">(.*?)</div>') #問題排名 findtitle = re.compile(r'<h1 class="css-3yucnr">(.*?)</h1>') #問題標題 findintroduce = re.compile(r'<div class="css-1o6sw4j">(.*?)</div>') #簡要介紹 findscore = re.compile(r'<div class="css-1iqwfle">(.*?)</div>') #熱門評分 findimg = re.compile(r'<img class="css-uw6cz9" src="(.*?)"/>') #文章配圖 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): # 設置請求頭 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()
到此這篇關於如何使用python爬取知乎熱榜Top50數據的文章就介紹到這瞭,更多相關python 爬取知乎內容請搜索WalkonNet以前的文章或繼續瀏覽下面的相關文章希望大傢以後多多支持WalkonNet!
推薦閱讀:
- 如何使用python爬取B站排行榜Top100的視頻數據
- 用Python實現爬取百度熱搜信息
- Python自動爬取圖片並保存實例代碼
- Python 批量下載陰陽師網站壁紙
- Python進階篇之正則表達式常用語法總結