python抓取內涵段子文章

標籤：max   close   urllib   write   ==   item   www.   python   count   

# coding:utf-8from urllib.request import urlretrieveimport threadingimport requestsfrom bs4 import BeautifulSoupfrom datetime import datetimeimport pymysqlimport randomimport  jsonimport  timenumber=0def GetArticel():    max_time = 1519404642    data = requests.get("http://www.neihanshequ.com/joke/?is_json=1&app_name=neihanshequ_web&max_time=" + str(max_time))    soup = BeautifulSoup(data.text, ‘html5lib‘)    #print(soup.select_one(‘body‘).get_text())    global number    jsondata=json.loads(str(soup.select_one(‘body‘).get_text()))    articleList=jsondata[‘data‘][‘data‘]    f = open("article.txt", ‘a‘,encoding=‘utf-8‘)    for item in articleList:       number+=1       #print(number)       f.write(item[‘group‘][‘content‘]+‘\n\n\n‘)       print(number)    f.close()        # print(count)        # print(item)if __name__ == ‘__main__‘:   for i in range(1,10):    print(i)    #GetArticel()    #time.sleep(1)

　　

python抓取內涵段子文章