selenium_采集药品数据1_采集第一页表格

Python爬虫视频教程零基础小白到scrapy爬虫高手-轻松入门

https://item.taobao.com/item.htm?spm=a1z38n.10677092.0.0.482434a6EmUbbW&id=564564604865

 

# -*- coding: utf-8 -*-
"""
Created on Sat May  7 09:32:30 2016

@author: daxiong
"""

import requests,bs4,csv,time,selenium
from selenium import webdriver
site1="http://118.114.237.85:8081/searchbio.aspx"
charset="gb2312"
browser=webdriver.Firefox()
browser.get(site1)
 
elems=browser.find_elements_by_class_name("tb")
elems1= elems[1:]
content=[i.text for i in elems1]


#功能：将list对象N等分  
def div_list(ls,n):  
    if not isinstance(ls,list) or not isinstance(n,int):  
        return []  
    ls_len = len(ls)  
    if n<=0 or 0==ls_len:  
        return []  
    if n > ls_len:  
        return []  
    elif n == ls_len:  
        return [[i] for i in ls]  
    else:  
        j = int(ls_len/n)    
        ls_return = []  
        for i in range(0,(n-1)*j,j):  
            ls_return.append(ls[i:i+j])  
        #算上末尾的j+k  
        ls_return.append(ls[(n-1)*j:])  
        return ls_return 
        
        
def Write_table_to_csv(fileName,list_tableContent):
    #对列表格式修改，字符串写入的格式不对
    file=open(fileName,'w',newline='')
    writer1=csv.writer(file)
    writer1.writerows(list_tableContent)
    file.close()          
        
content1=div_list(content,20)
Write_table_to_csv("1.csv",content1)