爬取猫途鹰

利用 BeautifulSoup + Requests 爬取 猫途鹰

一、用 BeautifulSoup 的 find_all()

from bs4 import BeautifulSoup
import requests
import time

url = 'https://cn.tripadvisor.com/Attractions-g60763-Activities-New_York_City_New_York.html'
wb_data = requests.get(url)
soup = BeautifulSoup(wb_data.text,'lxml')
titles    = soup.find_all('div', class_="property_title")
imgs      = soup.find_all('img', width="160")
cates = soup.find_all('div', class_="p13n_reasoning_v2")


for title,img,cate in zip(titles,imgs,cates):
            data = {
                'title'  :title.get_text().strip(),
                'img'    :img.get('src'),                                  #获得 src 内文本方法
                'cate'   :cate.get_text().replace('\n', ',')
                }
            print(data)

二、 用 BeautifulSoup 的 select

CSS选择器爬

from bs4 import BeautifulSoup
import requests
import time

url_saves = 'http://www.tripadvisor.com/Saves#37685322'
url = 'https://cn.tripadvisor.com/Attractions-g60763-Activities-New_York_City_New_York.html'
urls = ['https://cn.tripadvisor.com/Attractions-g60763-Activities-oa{}-New_York_City_New_York.html#ATTRACTION_LIST'.format(str(i)) for i in range(30,930,30)]

headers = {
    'User-Agent':'',
    'Cookie':''
}


def get_attractions(url,data=None):
    wb_data = requests.get(url)
    time.sleep(4)
    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')

    if data == None:
        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)


def get_favs(url,data=None):
    wb_data = requests.get(url,headers=headers)
    soup      = BeautifulSoup(wb_data.text,'lxml')
    titles    = soup.select('a.location-name')
    imgs      = soup.select('div.photo > div.sizedThumb > img.photo_image')
    metas = soup.select('span.format_address')

    if data == None:
        for title,img,meta in zip(titles,imgs,metas):
            data = {
                'title'  :title.get_text(),
                'img'    :img.get('src'),
                'meta'   :list(meta.stripped_strings)
            }
            print(data)

for single_url in urls:
    get_attractions(single_url)

三、从移动端爬取

# from mobile web site      
'''
headers = {
    'User-Agent':'', #mobile device user agent from chrome
}


mb_data = requests.get(url,headers=headers)
soup = BeautifulSoup(mb_data.text,'lxml')
imgs = soup.select('div.thumb.thumbLLR.soThumb > img')
for i in imgs:
    print(i.get('src'))
'''