爬虫：requests & BeautifulSoup 实战案例

爬取猫途鹰旅游网站：https://www.tripadvisor.cn/Attractions-g60763-Activities-New_York_City_New_York.html景点信息

from bs4 import BeautifulSoup
import requests

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,'html.parser')
    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)

PC端爬取信息容易受到限制，若爬取失败，可尝试移动端

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'))

headers 提供网页爬取时的头部信息，让对方识别为人的操作。

在谷歌浏览器里输入chrome://version,就可以看到用户代理，将用户代理添加到头部信息。