【Python】网页数据爬取实战

由于网页结构跟之前有变化,还不是很熟悉。代码待完善,问题记录:

  • 腾讯新闻二级网页内容爬取有问题。
  • 链家网站头文件没有用到。

爬取一条腾讯视频的header内容,存入txt。要求:

  1. 包含网页链接
  2. 包含title
  3. 包含所有headers信息
import requests
from bs4 import BeautifulSoup

u = 'http://news.qq.com/a/20170205/023923.htm'
r = requests.get(url = u)
headers = r.headers #获取网页头部信息
#print(headers)
soup =  BeautifulSoup(r.text,'lxml')
title = soup.title.text #获取网页title内容
#print(title)
f = open('C:\\Users\\Administrator\\Desktop\\lianxi\\header.txt','w',encoding='utf8')
f.seek(0)
# 创建一个txt文件

f.write('爬取网页:'+str(u)+'\n')
f.write('新闻标题为:'+title+'\n')

for i in headers:
    lst = [i,':',headers[i],'\n']
    f.writelines(lst)

f.close()
print('finished!')

爬取腾讯新闻网站上,某一天的某类新闻标题。要求:

  1. 开头:‘XX年XX月XX日腾讯新闻’
  2. 包括新闻标题和网址
    (爬取每一条新闻的内容(二级标题))
import requests
from bs4 import BeautifulSoup
import re

u = 'http://news.qq.com/world_index.shtml'
r = requests.get(url = u)
soup = BeautifulSoup(r.text,'lxml')
f = open('C:\\Users\\Administrator\\Desktop\\lianxi\\news.txt','w',encoding='utf8')
f.seek(0)
# 创建一个txt文件

f.write('2018年8月26日腾讯新闻\n')

news = soup.find_all('a',href=re.compile('http://news.qq.com/a/20180825/'))
#print(news)

for i in news:
    #print(i)
    txt = i.text.strip()#strip() 用于去掉前后空格
    if  txt =='':
        continue
    else:
        lst = [txt,',','url=',i.attrs['href']]
        f.writelines(lst)
    
f.close()
print('finished!')

修改

import requests
from bs4 import BeautifulSoup
import re

u = 'http://news.qq.com/world_index.shtml'
r = requests.get(url = u)
soup = BeautifulSoup(r.text,'lxml')
f = open('C:\\Users\\Administrator\\Desktop\\lianxi\\news.txt','w',encoding='utf8')
f.seek(0)
# 创建一个txt文件

f.write('2018年8月26日腾讯新闻\n')

news = soup.find_all('a',href=re.compile('//new.qq.com/omn/20180826'))
#print(news)

for i in news:
    #print(i)
    txt = i.text.strip()#strip() 用于去掉前后空格
    if  txt =='':
        continue
    else:
        lst = [txt,',','url=','http:',i.attrs['href'],'\n']
        f.writelines(lst)
    
f.close()
print('finished!')

添加正文内容:

import requests
from bs4 import BeautifulSoup
import re

u = 'http://news.qq.com/world_index.shtml'
r = requests.get(url = u)
soup = BeautifulSoup(r.text,'lxml')
f = open('C:\\Users\\Administrator\\Desktop\\lianxi\\news2.txt','w',encoding='utf8')
f.seek(0)
# 创建一个txt文件

f.write('2018年8月26日腾讯新闻\n')

news = soup.find_all('a',href=re.compile('http://news.qq.com/a/2018'))
#print(news)

for i in news:
    #print(i)
    txt = i.text.strip()#strip() 用于去掉前后空格
    if  txt =='':
        continue
    else:
        ul = i.attrs['href']
        ur = requests.get(url = ul)
        usoup = BeautifulSoup(ur.text,'lxml')  
        f.write(txt+'\n')
        #打印正文
        f.write('正文如下:\n')
        
        if usoup.body.attrs[id]=='P-QQ':#排除图片新闻
            continue
        else:
            p = usoup.find('div',id="Cnt-Main-Article-QQ").find_all('p')
            for i in p:
                print(i.text)
                f.write(i.text+'\n')
    f.write('\n')
f.close()
print('finished!')
爬虫正确的习惯和逻辑
  • 函数式爬取
  • 用浏览器去访问,headers信息
    r = request.get(url='...',headers={...})以浏览器的形式向网页进行请求
    头部信息

headers = input("粘贴头部信息:")
lst = headers.split('\n')
m=[]
for i in lst:
    key = i.split(':')[0]
    value = i.split(':')[1]
    m.append([str(key),str(value)])

print(dict(m))
def header_format(h):
    """
    函数用于转译网页headers信息
    h:输入的headers信息
    """
    h = input("粘贴头部信息:")
    lst = h.split('\n')
    m=[]
    for i in lst:
        key = i.split(':')[0]
        value = i.split(':')[1]
        m.append([str(key),str(value)])
    return(dict(m))

print(header_format(headers))
用函数式写法的优点:
  • 阅读性更强
  • 函数的可复制性
  • 便于修改

爬取一条腾讯视频的header内容,存入txt。函数式编写:

  1. 包含网页链接
  2. 包含title
  3. 包含所有headers信息

爬取链家二手房数据-深圳

import requests
from bs4 import BeautifulSoup
import re

def url_analysis(u, h, s, n):
    '''
    用于分析网页,最后得到一个含有二级网址的标签列表
    u:起始网址
    h:头部信息
    s:二级网址包含特定字段
    n:页码
    '''
    url_lst=[]
    for i in range(1,n+1):
        if i == 1:
            r = requests.get(url=u+'nb1rs深圳/') 
        else:
            r = requests.get(url=u+'pg'+str(i)+'nb1rs深圳/')
        soup = BeautifulSoup(r.text,'lxml')
        r2 = soup.find_all('a',href=re.compile(s))
        for j in r2:
            r3 = j.attrs['href']
            url_lst.append(r3)
        return(url_lst)

def content(u,h):
    '''
    爬取网页标签信息
    u:爬取的二级网址
    h:头部信息
    '''
    r = requests.get(url=u)
    r.encodinge = 'utf-8'
    soup = BeautifulSoup(r.text,'lxml')
    t = soup.title.text #爬取标题
    toprice = soup.find('div',class_='price').find('span',class_='total').text
    unprice = soup.find('div',class_='unitPrice').find('span',class_='unitPriceValue').text
    area = soup.find('div',class_='area').find('div',class_='mainInfo').text
    base = soup.find('div',class_='base').find('div',class_='content').find_all('li')
    year = base[-1].text
    pattern = 'resblockPosition:\'(.*?)\','               #.*?任意字符
    position =re.search(pattern,r.text).group(1)
    lng = position.split(',')[0]
    lat = position.split(',')[1]
    return([t,',', toprice,',', unprice,',', area,',', year,',',lng,',',lat,'\n'])                   
                      
    


if __name__ == '__main__': #main函数
    web_u = 'https://sz.lianjia.com/ershoufang/'
    web_h = {
             'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
             'Accept-Encoding': 'gzip, deflate, br', 
             'Accept-Language': 'zh-CN,zh;q=0.9',
             'Connection': 'keep-alive',
             'Cookie': 'TY_SESSION_ID=93f5b43a-5dc9-4d96-b57a-a4eb78f8dc15; lianjia_uuid=614ed9e0-dc25-421f-ba8b-141c574dbb47; _smt_uid=5b80defd.8430805; UM_distinctid=1656f670d3e4ff-02814a7ed21053-b34356b-1fa400-1656f670d3fdd7; _jzqx=1.1535172349.1535172349.1.jzqsr=bj%2Elianjia%2Ecom|jzqct=/.-; _ga=GA1.2.50227061.1535172352; ljref=pc_sem_baidu_ppzq_x; lianjia_ssid=dbe87b29-353a-45c2-97cf-aae666e2771b; Hm_lvt_9152f8221cb6243a53c83b956842be8a=1535172349,1535201139,1535358484; _jzqa=1.3976151446564617700.1535172349.1535201139.1535358484.3; _jzqc=1; _jzqy=1.1535201139.1535358484.1.jzqsr=baidu|jzqct=%E9%93%BE%E5%AE%B6%E7%BD%91.-; _jzqckmp=1; _gid=GA1.2.1182771159.1535358486; select_city=440300; all-lj=c32edd623b8a5a59c7de54c92107bb6c; _qzjc=1; CNZZDATA1255849469=275538323-1535355329-%7C1535355329; CNZZDATA1254525948=1806440598-1535354494-%7C1535354494; CNZZDATA1255633284=72361912-1535358081-%7C1535358081; CNZZDATA1255604082=1229464985-1535356409-%7C1535356409; Hm_lpvt_9152f8221cb6243a53c83b956842be8a=1535359605; _qzja=1.1736056849.1535358739249.1535358739249.1535358739249.1535359600160.1535359605575.0.0.0.10.1; _qzjb=1.1535358739249.10.0.0.0; _qzjto=10.1.0; _jzqb=1.15.10.1535358484.1',
             'Host': 'sz.lianjia.com',
             'Referer': 'https',
             'Upgrade-Insecure-Requests': '1',
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'
             }
    web_s = 'https://sz.lianjia.com/ershoufang/105'
    web_n = 3
    
    f = open('C:\\Users\\Administrator\\Desktop\\lianxi\\lianjia.txt','w')
    f.seek(0)
    f.write('title,total_price万元,unprice元/平方米,area平方米,产权年限,lng,lat\n')
    for i in url_analysis(web_u, web_h, web_s, web_n):
        data = content(i,web_h)
        f.writelines(data)
        print(data)
    f.close()
    print('finished!')

推荐阅读更多精彩内容