Python 爬虫学习1

from bs4 import BeautifulSoupimport requestsimport time#url = 'http://www.tripadvisor.cn/Attractions-g60763-Activities-New_York_City_New_York.html'#根据页数确定范围urls =['http://www.tripadvisor.cn/Attractions-g60763-Activities-oa{}-New_York_City_New_York.html#ATTRACTION_LIST'.format(str(i)) for i in range(0,1080,30)]
def get_attractions(url , data=None):    wb_data = requests.get(url)    time.sleep(4) #设定延时    soup = BeautifulSoup(wb_data.text, 'lxml')    titles = soup.select('div.PRoperty_title > a[target="_blank"]')    imgs = soup.select('img[width="160"]')    cates = soup.select('div.p13n_reasoning_v2 > a')    for title , img , cate in zip(titles , imgs , cates):        data = {            'title': title.get_text(),            'img': img.get('src'),            'cate': list(cate.stripped_strings)        }        print(data)
for i in urls:    get_attractions(i)
新手学习Python，了解网页元素，难点：元素定位