一、獲取到網絡上的網頁

from bs4 import  BeautifulSoup
import requests

url = ‘https://www.tripadvisor.cn/Attractions-g60763-Activities-New_York_City_New_York.html‘
web_data = requests.get(url)
soup = BeautifulSoup(web_data.text,‘lxml‘)
print(soup)

二、獲取想要的數據

from bs4 import  BeautifulSoup
import
 
 requests

url = ‘https://www.tripadvisor.cn/Attractions-g60763-Activities-New_York_City_New_York.html‘
web_data = requests.get(url)
soup = BeautifulSoup(web_data.text,‘lxml‘)
titles = soup.select(‘#taplc_attraction_coverpage_attraction_0 > div:nth-of-type(1) > div > div > div.shelf_item_container > div:nth-of-type(1) > div.poi > div > div.item.name > a
 
‘)
print(titles)

但不是所有的，使用下面的方式獲取所有

from bs4 import  BeautifulSoup
import requests

url = ‘https://www.tripadvisor.cn/Attractions-g60763-Activities-New_York_City_New_York.html‘
web_data = requests.get(url)
soup = BeautifulSoup(web_data.text,‘lxml‘)
titles = soup.select(‘div.item.name‘)
imgs 
 
= soup.select(‘img[width="200"]‘)
cates = soup.select(‘div.poi > div > div:nth-of-type(3)‘)
#taplc_attraction_coverpage_attraction_0 > div:nth-child(1) > div > div > div.shelf_item_container > div:nth-child(4) > div.poi > div > div:nth-child(3)
# print(titles,imgs,cates,sep=‘\n-----------\n‘)
#驗證下
# for title in titles:
#     print(title.get_text())
# for img in imgs:
#     print(img.get(‘src‘))
# for cate in cates:
#     print(cate.get_text())
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)

二、偽造登陸

三、爬取多個網頁

四、應對js-爬取手機端

二、抓取網絡上的資源信息