前言
工欲善其事,必先利其器。学习了python爬虫的基础知识和spss分析工具后,动手写代码爬取数据进行spss分析才能更好掌握工具的使用,提升自己。我选择了一个游戏网站,爬取其手机网游的信息,以此分析影响手机网游评分的因素。
1.数据的爬取
import requests
from bs4 import BeautifulSoup
import json
from openpyxl import Workbook
import numpy as np
import time
list = []
# User Agents
hds = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36',
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding':'gzip, deflate',
'Accept-Language':'zh-CN,zh;q=0.9',
'Connection':'keep-alive',
'Cookie':'BAIDU_SSP_lcr=https://www.baidu.com/link?url=zpwXeCd_RRY2FRQqCVYtuGPcbzYeeabv1UG4aKzI2tdzCbbJPbxXtJc0gsr1KS62&wd=&eqid=d4b30eca0005872c000000055b8f7a0c; Hm_lvt_15b67ce53ef6efd896a81316b10e56a4=1536129772; sec_tc=AQAAANxpbiKZXAcAQoUnd+/VZgti2ZRL; Hm_lpvt_15b67ce53ef6efd896a81316b10e56a4=1536131556'
}
'''
获得安卓游戏的详细信息所在网址链接
'''
def download(url):
url_list = []
try:
r = requests.request("get", url, headers = hds)
source_code = r.text
#print(source_code)
except Exception as e:
print(e)
try:
i = 0 # 计数器
soup = BeautifulSoup(r.text,'lxml')
div = soup.find_all('div',{
'class':'list_con'})