selenium爬取豆瓣电影 保存CSV格式
from selenium import webdriver
import csv
from multiprocessing import Pool
fp = open("电影.csv",'a')
write = csv.writer(fp)
write.writerow(['电影名称','评分','评论人数','代表名言','电影信息'])
brower = webdriver.Chrome('C:\Program Files\Google\Chrome\Application\Chromedriver.exe')
def get(URL):
try:
brower.get(URL)
title = brower.find_elements_by_css_selector('div.hd')
pingfeng = brower.find_elements_by_css_selector('span.rating_num')
pinglunrenshu = brower.find_elements_by_css_selector('div.star') # 评分加评论人数
daiiaominyan = brower.find_elements_by_css_selector('span.inq')
movieino = brower.find_elements_by_css_selector('div.bd')
for titl,pingfen,pinglunrensh,daiiaominya,mov in zip(title,pingfeng,pinglunrenshu,daiiaominyan,movieino):
write.writerow([titl.text,pingfen.text,pinglunrensh.text[3:],daiiaominya.text,mov.text])
except UnicodeEncodeError:
pass
if __name__ == '__main__':
url_list = ['https://movie.douban.com/top250?start={0}&filter='.format(i*25) for i in range(10)]
for url in url_list:
get(url
)
print("爬取成功")