单线程 爬去豆瓣250
import requests
from lxml import etree
from threading import Thread
import time
from queue import Queue
#单线程
base_url='https://movie.douban.com/top250?filter=&start='
movie_list=[]
for i in range(10):
url1=base_url+str((i*25))
response=requests.get(url=url1)
content=response.content
#接收数据
content=content.decode('utf-8')
html1 = etree.HTML(content)
item_list=html1.xpath('//div[@class="item"]')
for item in item_list:
movie = {}
movie['编号'] = item.xpath('./div[1]/em/text()')[0]
movie['名称'] = item.xpath('./div[2]//a/span[1]/text()')[0]
movie['评分'] = item.xpath('./div[2]//span[@class="rating_num"]/text()')[0]
movie_list.append(movie)
print(len(movie_list))
#多线程
def douban(url1):
response = requests.get(url=url1)
content=response.content
#接收数据
content=content.decode('utf-8')
html1 = etree.HTML(content)
item_list=html1.xpath('//div[@class="item"]')
for item in item_list:
movie = {}
movie['编号'] = item.xpath('./div[1]/em/text()')[0]
movie['名称'] = item.xpath('./div[2]//a/span[1]/text()')[0]
movie['评分'] = item.xpath('./div[2]//span[@class="rating_num"]/text()')[0]
#自动创建锁防止多线程执行造成存储数据时发生混乱
movie_list.put(movie)
if __name__ == '__main__':
start_time=time.time()
movie_list = Queue()
base_url = 'https://movie.douban.com/top250?filter=&start='
movie_list=[]
thread_list=[]
for i in range(10):
url1=base_url+str((i*25))
thread_spider=Thread(target=douban,args=[url1])
thread_list.append(thread_spider)
thread_spider.start()
for thread_one in thread_list:
thread_one.join()
#防止主进程先运行到这句话,所以需要让住主进程等待子进程
end_time = time.time()
while not movie_list.empty():
print(movie_list.get())
print('爬取时间总结：%s' % (end_time - start_time))
#利用协程爬取数据
import requests
import json
import time
from lxml import etree
from threading import Thread
from queue import Queue
from gevent import monkey
import gevent
import random
# gevent 让我们可以按同步的方式来写异步程序
# monkey.patch_all() 会在Python程序执行时动态的将网络库（socket,select,thread)
# 替换掉，变成异步的库，让我们的程序可以异步的方式处理网络相关的任务
monkey.patch_all()
def spider(url):
response = requests.get(url=url,headers=headers,proxies = {'http':random.choice(proxies_ips)})
content = response.content
content = content.decode('utf-8')
'''数据处理'''
html = etree.HTML(content)
item_list = html.xpath('//div[@class="item"]')
for item in item_list:
movie = {}
movie['编号'] = item.xpath('./div[1]/em/text()')[0]
print(movie['编号'])
movie['名称'] = item.xpath('./div[2]//a/span[1]/text()')[0]
movie['评分'] = item.xpath('./div[2]//span[@class="rating_num"]/text()')[0]
movie_list.put(movie)
if __name__ == '__main__':
proxies_ips = [
'http://122.114.31.177:808',
'http://61.135.217.7:80',
'http://14.20.180.209:8118',
]
headers={
'Host':'movie.douban.com',
'Referer':'https://accounts.douban.com/login?redir=https://movie.douban.com/top250?filter=&source=None',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
}
start_time = time.time()
# 存储数据
movie_list = Queue()
'''发送请求'''
base_url = 'https://movie.douban.com/top250?filter=&start='
gevent_spiders = []
for i in range(10):
url = base_url + str(i * 25)
print(url)
gevent_spider = gevent.spawn(spider,url)
gevent_spiders.append(gevent_spider)
gevent.joinall(gevent_spiders)
end_time = time.time()
print('爬取时间总结：%s' % (end_time - start_time))
