def crawl(self):
# time = 20
url = self.que.get()
if url not in self.visited:
if self.rlock.acquire():
self.visited.add(url)
self.rlock.release()
else:
return
try:
# html = urllib.request.urlopen(url).read().decode('gbk')
req = urllib.request.Request(url, headers={
'Connection': 'Keep-Alive',
'Accept': 'text/html, application/xhtml+xml, */*',
'Accept-Language': 'en-US,en;q=0.8,zh-Hans-CN;q=0.5,zh-Hans;q=0.3',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko'
})
html = urllib.request.urlopen(req, timeout=30).read().decode('gbk')
if html:
soup = BeautifulSoup(html, 'lxml')
if self.is_news_url(url):
# print(self.news)
print(url)
if url not in self.news:
news = News(soup, url)
lenth = len(news.content)
if lenth > 0:
try:
news.add()
if self.rlock.acquire():
self.news.add(url)
self.rlock.release()
except Exception as e:
raise e
else:
print(url + ' is exist')
links = soup.find_all('a')
for link in links:
# get url in link
link_url = link.get('href')
if self.is_crawl_url(link_url):
# print(link_url)
# insert into the queue
# self.is_news_url(link_url)
if not self.is_news_url(link_url):
self.que.put(link_url)
else:
self.que.put(self.is_news_url(link_url))
except Exception as e:
if self.is_news_url(url):
print('err:' + url)
print('exception:' + str(e))
# coding:utf-8 from JLQueue import JLQueue from JLThread import ThreadPool from JLModel import News from JLModel import app g_news = News.get_all_news() g_queue = JLQueue() g_visited = set() # g_news = set() g_threads = [] inital_url = 'http://news.163.com/' g_queue.put(inital_url) g_threadpool = ThreadPool(11, g_threads, g_queue, g_visited, g_news) g_threadpool.start() # run server # JLServer.run() app.run(host="127.0.0.1", port=25000) g_threadpool.wait_for_complete() # print(g_visited)
