概述
Python在处理CSV文件时,如果writerow的对象是<type 'unicode'>字符串时,写入到CSV文件时将会出现一个字符占一个单元格的情况:
但是将字符串转换为列表类型时,进行writerow写入即可实现,writerow一个列表只占一个单元格:
代码:
#encoding=utf-8 #不打开浏览器进行操作 import sys,csv,codecs import time from lxml import etree reload(sys) sys.setdefaultencoding('utf-8') from selenium import webdriver option = webdriver.ChromeOptions() option.add_argument("headless") driver = webdriver.Chrome(chrome_options=option) # driver = webdriver.Chrome() driver.get("https://www.kanzhun.com/xs/?ka=head-salary") print([driver.title]) #打开CSV文件 csvfile=codecs.open('C:UsersDesktop est.csv','wb','gbk') writer = csv.writer(csvfile) writer.writerow(driver.title) #获取城市工资排名 aa=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[1]/dd/ul/li/i') bb=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[1]/dd/ul/li/a') cc=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[1]/dd/ul/li/span') print('======地区工资排行(TOP10)======') writer.writerow([u'======地区工资排行(TOP10)======']) for (i,o,p) in zip(aa,bb,cc): i = i.text o = o.text p = p.text print(type(p)) ss = [i, o, p] writer.writerow(ss) print(i+'...'+o+'...'+p) #获取公司工资排名 aa=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[2]/dd/ul/li/i') bb=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[2]/dd/ul/li/a') cc=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[2]/dd/ul/li/span') print('======公司工资排行(TOP10)======') writer.writerow([u'======公司工资排行(TOP10)======']) for (i,o,p) in zip(aa,bb,cc): i = i.text o = o.text p = p.text ss = [i, o, p] writer.writerow(ss) print(i+'...'+o+'...'+p) #获取职位工资排名 aa=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[3]/dd/ul/li/i') bb=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[3]/dd/ul/li/a') cc=driver.find_elements_by_xpath('/html/body/div/section[1]/div[3]/dl[3]/dd/ul/li/span') print('======职位工资排行(TOP10)======') writer.writerow([u'======职位工资排行(TOP10)======']) for (i,o,p) in zip(aa,bb,cc): i = i.text o = o.text p = p.text ss = [i,o,p] writer.writerow(ss) print(i+'...'+o+'...'+p) csvfile.close() driver.quit()
CSV文件:
注意:
其中开头的reload(sys)和打开csv文件时的‘gbk’都是辅助解决字符编码问题的。