def Notification_sdcs(url, page, start=1, end=5):
global sdcs_dict
url += "%s"
signal = 1
for i in range(start, end):
if i % 2 == 0:
try:
tagpage = url % i
req = urllib.request.Request(url=page, headers=headers)
c = urllib.request.urlopen(req)
read_soup = BeautifulSoup(c.read(),
"html.parser",
from_encoding="utf-8")
#print read_soup
search_list = read_soup.find_all(id=tagpage)[0]
#print search_list
dl = search_list("ul")[0]
for li in dl("li"):
date = li.find_all("span")
try:
#print li.find_all("a")[0]["title"]
if li.find_all(
"a")[0]["title"] not in sdcs_dict.keys():
print("hehe")
sdcs_dict[li.find_all("a")[0]
["title"]] = date[0].get_text()
iMessage.send_Message(
News=li.find_all("a")[0]["title"],
sub='News From SDCS')
#iMessage.send_Message(News='News From SDCS')
signal = 0
else:
continue
except Exception:
msg = traceback.format_exc()
if li.find_all(
"a")[0].get_text() not in sdcs_dict.keys():
sdcs_dict[li.find_all("a")
[0].get_text()] = date[0].get_text()
print("xixi")
signal = 0
iMessage.send_Message(
News=li.find_all("a")[0].get_text(),
sub='News From SDCS')
#iMessage.send_Message(News='News From SDCS')
else:
continue
except Exception:
msg = traceback.format_exc()
print(msg)
if signal == 1:
print("No News From SDCS!")
def JudgeNews():
signal = 0
links = getSWREgnews() # 调用getSWREnews()函数获取信息
for i in links:
if i.get('title') not in NewsTitle: # 对新调用函数后获得的links遍历，
signal = 1 # 将signal标志为1，方便接下来情况并重新保存NewsTitle
url = 'http://www.swre.cugb.edu.cn/' + i.get('href')
content = Article(url, language='zh')
content.download()
content.parse()
iMessage.send_Message(News=content.text + "\n" + url, sub='水环通告：' + i.get('title'))
# 将不存在于NewsTitle中的新闻发送至指定邮箱
if signal == 1: # 根据前面遍历后的signal信号
NewsTitle.clear() # 若为1,则清空NewsTitle列表
for i in links:
NewsTitle.append(i.get('title')) # 重新遍历links,将title保存至NewsTitle
# print(NewsTitle) 测试专用，否则请注释
t = Timer(300, JudgeNews) # 每300秒执行一次该函数
t.start()
print(NewsTitle)
class Crawl(object):
def __init__(self):
self.urls = url_manager.UrlManager()
self.downloader = html_downloader.HtmlDownloader()
self.parser = html_parser.HtmlParser()
self.outputer = html_outputer.HtmlOutputer()
def craw(self, root_urls):
count = 1
for root_url in root_urls:
self.urls.add_new_url(root_url)
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url()
print 'craw %d : %s' % (count, new_url)
html_cont = self.downloader.download(new_url)
new_urls, new_data = self.parser.parse(new_url, html_cont)
self.urls.add_new_urls(new_urls)
self.outputer.collect_data(new_data)
count = count + 1
except Exception, e:
print 'craw failed!'
#print 'str(Exception):\t', str(Exception)
#print 'str(e):\t\t', str(e)
#print 'repr(e):\t', repr(e)
#print 'e.message:\t', e.message
#print 'traceback.print_exc():'; traceback.print_exc()
#print 'traceback.format_exc():\n%s' % traceback.format_exc()
datass = self.outputer.output_html()
News = ''
for datas in datass:
for data in datas:
News += datas[data] + '\n'
#print News
if News != '':
iMessage.send_Message(News, 'CQUT_News')
def JudgeNews():
signal = 0
links1, links2, links3 = getCUGBgranews() # 调用getCUGBgranews()函数获取信息
# print(links1) #测试专用，否则请注释
# print(links2) #测试专用，否则请注释
# print(links3) #测试专用，否则请注释
for i, j, k in zip(links1, links2, links3):
if i.get('title') not in NewsTitle: # 对新调用函数后获得的links1遍历，
signal = 1 # 将signal标志为1，方便接下来情况并重新保存NewsTitle
url = 'https://www1.cugb.edu.cn/' + i.get('href')
content = Article(url, language='zh')
content.download()
content.parse()
iMessage.send_Message(News=content.text + "\n" + url,
sub='📌研院·培养与学籍：📢 ' + i.get('title'))
# 将不存在于NewsTitle中的新闻发送至指定邮箱
if j.get('title') not in NewsTitle:
signal = 1 # 将signal标志为1，方便接下来情况并重新保存NewsTitle
url = 'https://www1.cugb.edu.cn/' + j.get('href')
content = Article(url, language='zh')
content.download()
content.parse()
iMessage.send_Message(News=content.text + "\n" + url,
sub='📌研院·学科与学位：📢 ' + j.get('title'))
if k.get('title') not in NewsTitle:
signal = 1 # 将signal标志为1，方便接下来情况并重新保存NewsTitle
url = 'https://www1.cugb.edu.cn/' + k.get('href')
content = Article(url, language='zh')
content.download()
content.parse()
iMessage.send_Message(News=content.text + "\n" + url,
sub='📌研院·通知公告：📢 ' + k.get('title'))
# 将不存在于NewsTitle中的新闻发送至指定邮箱
if signal == 1: # 根据前面遍历后的signal信号
NewsTitle.clear() # 若为1,则清空NewsTitle列表
for i, j, k in zip(links1, links2, links3):
NewsTitle.append(i.get('title')) # 重新遍历links,将title保存至NewsTitle
NewsTitle.append(j.get('title')) # 重新遍历links,将title保存至NewsTitle
NewsTitle.append(k.get('title')) # 重新遍历links,将title保存至NewsTitle
# print(NewsTitle) #测试专用，否则请注释
t = Timer(300, JudgeNews) # 每300秒执行一次该函数
t.start()
elif index == 3:
news = "\n\n【研院通知·学位与学科】" + "\n"
for i in links:
No = No + 1
news = news + "\n" + str(No) + "、" + i.get('title') + \
" ☛" + "https://www1.cugb.edu.cn/" + i.get('href')
elif index == 4:
news = "\n\n【研院通知·通知公告】" + "\n"
for i in links:
No = No + 1
news = news + "\n" + str(No) + "、" + i.get('title') + \
" ☛" + "https://www1.cugb.edu.cn/" + i.get('href')
elif index == 5:
news = "\n\n【水环通知】" + "\n"
for i in links:
No = No + 1
news = news + "\n" + str(No) + "、" + i.get('title') + \
" ☛" + "http://www.swre.cugb.edu.cn/" + i.get('href')
return news
if __name__ == "__main__":
CUGBznews = getCUGBznews()
CUGBgnews = getCUGBgnews()
CUGBdnews = getCUGBdnews()
CUGBnotice = getCUGBnotice()
SWREnotice = getSWREnotice()
news = CUGBznews + CUGBgnews + CUGBdnews + CUGBnotice + SWREnotice
date = time.strftime("(%Y%m%d)", time.localtime(time.time()))
iMessage.send_Message(News=news, sub='地大研院今日要闻' + date)