采用協(xié)程來實現(xiàn)快速抓取頁面信息
出處：https://github.com/jingsupo/python-spider/blob/master/day07/douban/04douban_gevent.py
# -*- coding:utf-8 -*-
import requests, time, gevent
from lxml import etree
from gevent import monkey
monkey.patch_all()
class DoubanMovie(object):
def __init__(self):
self.base_url = "https://movie.douban.com/top250"
self.headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64; Trident/7.0; rv:11.0) like Gecko"}
# 電影總數(shù)量
self.count = 0
def send_request(self, url):
time.sleep(2)
try:
response = requests.get(url, headers=self.headers)
data = response.content
self.parse_data(data)
except Exception as e:
print e
def parse_data(self, data):
html_data = etree.HTML(data)
# 電影名字
name_list = html_data.xpath('//*[@id="content"]/div/div[1]/ol/li/div/div[2]/div[1]/a/span[1]/text()')
for name in name_list:
print name
# 每獲取一部電影名字電影數(shù)量增加1
self.count += 1
def run(self):
start_time = time.time()
gevent_list = []
for page in range(0, 225 + 1, 25):
url = self.base_url + '?start=' + str(page)
# 創(chuàng)建協(xié)程
gevents = gevent.spawn(self.send_request, url)
gevent_list.append(gevents)
# 主線程等待
gevent.joinall(gevent_list)
end_time = time.time()
total_time = end_time - start_time
print '全部電影%d部' % self.count
print '總時間%ss' % total_time
if __name__ == '__main__':
spider = DoubanMovie()
spider.run()