python爬虫学习第一周总结

Beatifulsoup中文文档：http://beautifulsoup.readthedocs.io/zh_CN/latest/

Requests官方文档（中文）：http://docs.python-requests.org/zh_CN/latest/user/quickstart.html

一、解析网页中的元素

beatifulsoup

右键copy selector或xpath，描述元素在网页中的什么位置什么位置

对xpath的理解

练习1

from bs4 import BeautifulSoup
import urllib

url = "http://www.mmjpg.com/"
html = urllib.request.urlopen(url)
response = html.read()
soup = BeautifulSoup(response,'lxml')
images = soup.select('body > div.main > div.pic > ul > li > a > img')
titles = soup.select('body > div.topbar > div.subnav > a')
#print(images)

for image in images:
    print(image.get('src'))

练习2

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(),#获得对应的文本
                'img'    :img.get('src'),#获得属性的值
                'cate'   :list(cate.stripped_strings),#获得标签下所以子节点的文本，为了存储，用列表表示
                }
        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)


# 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'))
'''

二、如何获得网页中的异步加载数据

点击XHR，在网页中下拉加载数据