def __init__(self):
self.mongo = MongoDB()
self.news_url_queue = news_url_Queue() # 存新闻url，用于多线程爬取
self.news_html_queue = news_url_Queue() # 存新闻html
self.old_day_news_queue = news_url_Queue()
# self.log = Logging('../helloword/static/sina').get_logging()
self.log = Logging('../Sina/sina.txt').get_logging()
def __init__(self):
if crawler_config.debug:
self.db = MongoDB('test_stock_crawler')
else:
self.db = MongoDB('stock_crawler')
self.url = ""
def store(self):
""" A function in this class to store a media, a movie or a show into the database """
client = MongoDB.setupConnection()
try:
db = client[DATABASE]
collection = db[COLLECTION]
return collection.insert_one(self).inserted_id
except Exception as error:
logger.Error("Error in Media class, store function: ", str(error))
finally:
MongoDB.closeConnection(client)
def remove(_id):
""" A function for removing a media from the database using its id."""
client = MongoDB.setupConnection()
db = client[DATABASE]
collection = db[COLLECTION]
try:
if _id:
return collection.remove({"_id": ObjectId(_id)})
except Exception as error:
logger.Error("Error in Media class, remove function: ", str(error))
finally:
MongoDB.closeConnection(client)
def read_data_from_coupon_db(self, id=None):
flag = 0
print "id = ",id
if not id:
return MongoDB().read_from_coupon_collection()
else:
for data_entry in MongoDB().read_from_coupon_collection():
if id in data_entry.values():
print "data_entry = ", data_entry
reqd_data = data_entry
flag = 1
if flag == 1:
del reqd_data['_id']
return reqd_data
else:
return 'Data not available'
def main():
m = MongoDB()
tasks = []
all_pairs = m.get_all_pairs()
for address in all_pairs[:100]:
pair = Web3.toChecksumAddress(address)
task = log_loop(pair, 60)
tasks.append(task)
print('{} Starting...'.format(len(tasks)))
loop = asyncio.get_event_loop()
try:
loop.run_until_complete(asyncio.gather(*tasks))
finally:
loop.close()
class Crawler:
def __init__(self):
if crawler_config.debug:
self.db = MongoDB('test_stock_crawler')
else:
self.db = MongoDB('stock_crawler')
self.url = ""
@property
def type(self):
return self.__class__.__name__
def insert_or_update(self, data):
log = logger.getChild( self.type + '.insert_or_update')
log.setLevel(logging.INFO)
log.debug('insert data: {}'.format(data))
collection = 'stock'
document = self.db.query(collection).find_one({'type': data['type'], 'date': data['date'], 'code': data['code']})
if document is None:
self.db.insert(collection, data=data)
log.debug('insert data: {}'.format(data))
def crawling(self, url, encoding='cp949'):
log = logger.getChild(self.type + 'crawling')
request = Request(url, headers={
'User-Agent':
'Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.9.0.1) '
'Gecko/2008071615 Fedora/3.0.1-1.fc9 Firefox/3.0.1'})
try:
handle = urlopen(request)
except URLError:
log.error('may be, url host changed: {}'.format(url))
return None
data = handle.read()
soup = BeautifulSoup(data.decode(encoding, 'ignore'), "html.parser", from_encoding="utf-8")
return soup
def crawl_zhilian(self, city, keyword):
#url_list = [] # todo url_list 做成堆栈形式
begin_url = 'https://fe-api.zhaopin.com/c/i/sou?start={page}&pageSize=90&cityId={city}&salary=0,0&workExperience=-1&education=-1&companyType=-1&employmentType=-1&jobWelfareTag=-1&kw={keyword}&kt=3'
database = MongoDB('zhilian', self.keywords[keyword])
url_list = self._get_list(begin_url, city, keyword, page_weight=90)
print(keyword, city, 'list parser done!')
print(len(url_list))
self._get_content(database, url_list)
def reload(_id, key, value):
""" A function to update a media based on its id. Attribute of the media as key and value of the attribute as
value will be passed to this function as its arguments as well as media id."""
global movie
client = MongoDB.setupConnection()
db = client[DATABASE]
collection = db[COLLECTION]
try:
if _id:
movie = collection.update_one({
'_id': _id
}, {
'$set': {
key: value
}
}, upsert=True) # To avoid inserting the same document more than once
return movie
except Exception as error:
logger.Error("Error in Media class, reload function: ", str(error))
finally:
MongoDB.closeConnection(client)
def retrieve(_id, key, value):
""" A function to retrieve a media, a movie or a show, using the media id or an attribute of the media or both
, id and an attribute. For the attribute of a media, a key and its value needs to be defined, like
'release year' as key and '2013' as its value."""
client = MongoDB.setupConnection()
try:
db = client[DATABASE]
logger.Info("Retrieved database: ", str(db))
collection = db[COLLECTION]
logger.Info("Retrieved collection: ", str(collection))
if _id is None:
medias = collection.find({key: value}).sort('_id', pymongo.ASCENDING)
result = []
for film in medias:
# logger.Info("Retrieved media: ", str(JSONEncoder().encode(film)))
result.append(film)
if len(result) == 1:
return JSONEncoder().encode(result[0])
elif len(result) > 1:
ms = []
for r in result:
ms.append(JSONEncoder().encode(r))
return ms
else:
return []
if key is None and value is None:
media = collection.find_one({"_id": ObjectId(_id)})
return JSONEncoder().encode(media)
if (_id is not None) and (key is not None) and (value is not None):
media = collection.find_one({"$and": [{"_id": ObjectId(_id)}, {key: value}]})
return JSONEncoder().encode(media)
except Exception as error:
logger.Error("Error in Media class, retrieve function: ", str(error))
finally:
MongoDB.closeConnection(client)
def handle_login(account):
conta = MongoDB.login(account["username"], account["password"])
if conta:
if conta["license"]['to_date'] < time.time():
Updater.expire_warning()
return False
conta['password'] = account["password"]
conta["license"]['from_date'] = datetime.fromtimestamp(
conta["license"]['from_date']).strftime('%d/%m/%Y')
conta["license"]['to_date'] = datetime.fromtimestamp(
conta["license"]['to_date']).strftime('%d/%m/%Y')
return conta
return False
def retrieveAll(key, value, limit, offset):
""" A function to retrieve all media, movies or shows, using an attribute of the media such as type For the
attribute of a media, a key and its value needs to be defined, like 'release year' as key and '2013'
as its value."""
client = MongoDB.setupConnection()
try:
db = client[DATABASE]
logger.Info("Retrieved database: ", str(db))
collection = db[COLLECTION]
logger.Info("Retrieved collection: ", str(collection))
# Setting up pagination based on limit and offset
starting = collection.find({key: value}).sort('_id', pymongo.ASCENDING)
L_id = starting[offset]['_id']
medias = collection.find({"$and": [{'_id': {"$gte": L_id}}, {key: value}]}).sort('_id', pymongo.ASCENDING).limit(limit)
result = []
for media in medias:
result.append(JSONEncoder().encode(media))
return result
except Exception as error:
logger.Error("Error in Media class, retrieve function: ", str(error))
finally:
MongoDB.closeConnection(client)
def crawl_liepin(self, city, keyword):
begin_url = "https://www.liepin.com/city-{city}/zhaopin/pn{page}/?d_pageSize=40&jobKind=2&key={keyword}"
database = MongoDB('liepin', self.keywords[keyword])
url_list = self._get_list(begin_url,
city,
keyword,
page_begin=0,
web_name='liepin')
print(keyword, city, 'list parser done!')
if url_list:
print(len(url_list))
self._get_content(database, url_list, web_name='liepin')
def crawl_qiancheng(self, city, keyword):
begin_url = 'https://search.51job.com/list/{city},000000,0000,00,9,99,{keyword},2,{page}.html?lang=c&postchannel=0000&workyear=99&cotype=99°reefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare='
database = MongoDB('qiancheng', self.keywords[keyword])
url_list = self._get_list(begin_url,
city,
keyword,
page_begin=1,
web_name='qiancheng')
print(keyword, city, 'list parser done!')
if url_list:
print(len(url_list))
self._get_content(database, url_list, web_name='qiancheng')
def get_all_status_thread(self,
status_list=[],
collect_name='status',
trim_user=True,
include_entities=True):
wrapper_func = handle_exception(self.get_status)
db = MongoDB().connect()
collect = db[collect_name]
while len(status_list) > 0:
status_id = status_list.pop(0)
status_obj = wrapper_func(status_id)
status = self.tweetobj_to_dict(status_obj)
if not status:
continue
try:
collect.insert_one(status)
except Exception as e:
continue
decimals = 18
except Exception as e:
traceback.print_exc()
sys.exit(-1)
print('{} {}({}) {}'.format(token, name, symbol, decimals))
doc = {
'address': token,
'name': name,
'symbol': symbol,
'decimals': decimals,
}
return doc
if __name__ == '__main__':
db = MongoDB()
tokens = db.get_all_tokens()
parse_tokens = []
for token in tokens:
if db.get_token(token) is None:
parse_tokens.append(token)
# if len(parse_tokens) == 6:
# break
print(len(parse_tokens))
with concurrent.futures.ThreadPoolExecutor() as executor:
futures = []
for token in parse_tokens:
futures.append(executor.submit(parse_token, token))
for future in concurrent.futures.as_completed(futures):
doc = future.result()
def get_user_all_timeline(self,
user_id=None,
collect_name="tweets_task",
screen_name=None,
include_rts=True,
exclude_replies=False):
if user_id == None and screen_name == None:
return None
if user_id:
try:
user_id = long(user_id)
except Exception as e:
print e
return None
flag = True
tweets = [0]
sleep_count = 0
db = MongoDB().connect()
collect = db[collect_name]
get_api = self.get_api
while len(tweets) > 0:
try:
if flag:
tweets = get_api().GetUserTimeline(
user_id=user_id,
screen_name=screen_name,
include_rts=include_rts,
exclude_replies=exclude_replies,
trim_user=True,
count=200)
flag = False
else:
tweets = get_api().GetUserTimeline(
user_id=user_id,
screen_name=screen_name,
include_rts=include_rts,
exclude_replies=exclude_replies,
trim_user=True,
count=200,
max_id=tweets[-1].id - 1)
except error.TwitterError as te:
try:
if te.message == 'Not authorized.':
print 'Not authorized.'
return
if te.message[0]['code'] == 88:
sleep_count += 1
if sleep_count >= API_COUNT:
print "sleeping..."
sleep_count = 0
time.sleep(300)
continue
else:
print te
break
except Exception as ee:
print ee
break
except Exception as e:
break
for tt in tweets:
tweet = self.tweetobj_to_dict(tt)
if not tweet:
continue
try:
collect.insert_one(tweet)
except Exception as e:
continue
def write_data_to_product_db(self, info):
MongoDB().write_to_product_collection(info)
logger.info(f'Converting: {src_collection.__name__} ({db.get_collection_size(src_collection)})'
f' -> {dst_collection.__name__} ({db.get_collection_size(dst_collection)})')
docs = src_collection.objects()
total_count = docs.count()
for current_count, src_doc in enumerate(docs):
log_progress(current_count, total_count)
try:
mapped_doc = map_document(src_doc)
except (DocumentConversionError, DocumentConstructionError) as e:
logger.warning(f'Skipping: {src_doc} because of: {e}')
continue
mapped_doc.create_or_update()
with db.connect():
logger.info(f'Total {dst_collection.__name__} count: ({db.get_collection_size(dst_collection)})')
logger.info(f'Documents.Conclusion count: ({db.get_collection_size(Documents.Conclusion)})')
logger.info(f'Documents.License count: ({db.get_collection_size(Documents.License)})')
if __name__ == '__main__':
logger = root_logger('convert_data', logging.INFO)
try:
db = MongoDB() # credentials for MongoDB can be set up here
convert_data(Documents.FileRaw, Documents.File)
logger.info('Success')
except Exception as e:
logger.info(e, exc_info=True)
def save_tweets(self, count=1):
database = MongoDB("verificacion")
coll = database.collection("tweets")
tweets = self._user_timeline(count)
for tweet in tweets:
coll.insert({"tweet": tweet})
# influx.py
import time
from datetime import datetime
import concurrent
from helper import DeFiContract
from web3 import Web3
from web3 import exceptions
from kfk import KafkaDB
from database import MongoDB
k = KafkaDB()
m = MongoDB()
def scrapReserves(pair_address):
pair = Web3.toChecksumAddress(pair_address)
contract = DeFiContract(pair, 'Pair')
r0, r1, _ = contract.getReserves()
print('{} {} {}'.format(pair, r0, r1))
doc = {
'address': pair,
'r0': r0,
'r1': r1,
't': datetime.utcnow().timestamp(),
}
return doc
while True:
async def get_and_store(self, device):
""" Get snmp infomation and add to database
"""
mongo = MongoDB()
host = device.ip
community = device.snmp_community
port = device.snmp_port
results = await asyncio.gather(
asyncio.ensure_future(get_system_info(host, community, port)),
asyncio.ensure_future(get_routes(host, community, port)),
asyncio.ensure_future(get_ip_addr(host, community, port)),
asyncio.ensure_future(get_interfaces(host, community, port)),
asyncio.ensure_future(get_cdp(host, community, port)),
# asyncio.ensure_future(get_lldp(host, community, port)), # Todo
)
if all(r is None for r in results):
logging.debug("SNMP Server for device ip %s is gone down", host)
return
system_info = results[0]
routes = results[1]
ip_addrs = results[2]
interfaces = results[3]
# CDP
cdp = results[4]
# LLDP
# lldp = results[5]
# Todo optimize this
# for if_index, interface in enumerate(interfaces):
# for ip_index, ip_addr in enumerate(ip_addrs):
# if interface['index'] == ip_addr['if_index']:
# interface['ipv4_address'] = ip_addr['ipv4_address']
# interface['subnet'] = ip_addr['subnet']
for if_index in range(len(interfaces)):
for ip_index in range(len(ip_addrs)):
if interfaces[if_index]['index'] == ip_addrs[ip_index][
'if_index']:
interfaces[if_index]['ipv4_address'] = ip_addrs[ip_index][
'ipv4_address']
interfaces[if_index]['subnet'] = ip_addrs[ip_index][
'subnet']
break
# print(interfaces[0])
my_device = mongo.db.device.find_one({'device_ip': host})
if my_device:
for interface in interfaces:
for my_interface in my_device['interfaces']:
if interface['description'] == my_interface['description']:
# In
in_octets = interface['out_octets'] - my_interface[
'out_octets']
in_in_time = system_info['uptime'] - my_device['uptime']
bw_in_usage_percent = sdn_utils.cal_bw_usage_percent(
in_octets, interface['speed'], in_in_time)
# Out
out_octets = interface['out_octets'] - my_interface[
'out_octets']
out_in_time = system_info['uptime'] - my_device[
'uptime']
bw_out_usage_percent = sdn_utils.cal_bw_usage_percent(
out_octets, interface['speed'], out_in_time)
# Add information
interface['bw_in_usage_octets'] = in_octets
interface['bw_in_usage_percent'] = bw_in_usage_percent
interface['bw_out_usage_octets'] = out_octets
interface[
'bw_out_usage_percent'] = bw_out_usage_percent
interface['bw_usage_update'] = time.time()
logging.debug(' || BW in usage %.3f || %d bytes',
bw_in_usage_percent, in_octets)
logging.debug(' || BW out usage %.3f || %d bytes',
bw_out_usage_percent, out_octets)
break
system_info['interfaces'] = interfaces
# Clear old routes
mongo.db.route.delete_many({'device_ip': host})
# Insert net routes
mongo.db.route.insert_many(routes)
mongo.device.update_one({'ipv4_address': host}, {'$set': system_info},
upsert=True)
# Insert CDP
mongo.db.cdp.update_one({'device_ip': host},
{'$set': {
'device_ip': host,
'neighbor': cdp
}},
upsert=True)
def drop_product_table(self):
MongoDB().drop_product_collection()
def write_data_to_coupon_db(self, info):
MongoDB().write_to_coupon_collection(info)
def getCookies(weibo):
db = MongoDB()
cookies = []
loginURL = 'https://passport.weibo.cn/signin/login'
if db.Cookies.count() < 10:
print '-----------------------------------------'
print 'Start crawl cookies'
print '-----------------------------------------'
for elem in weibo:
account = elem['no']
password = elem['psw']
item = {'account':account}
if db.find_cookie(item):
continue
try:
driver = webdriver.Chrome()
driver.get(loginURL)
time.sleep(2)
failure = 0
while "登录 - 新浪微博" in driver.title and failure < 5:
failure += 1
driver.set_window_size(1920, 1080)
username = driver.find_element_by_id("loginName")
username.clear()
username.send_keys(account)
psd = driver.find_element_by_id("loginPassword")
psd.clear()
psd.send_keys(password)
commit = driver.find_element_by_id("loginAction")
commit.click()
time.sleep(10)
# cookie=driver.get_cookies()
# print cookie
cookie = {}
if "微博 - 随时随地发现新鲜事" in driver.title:
for elem in driver.get_cookies():
cookie[elem["name"]] = elem["value"]
if len(cookie) > 0:
item = {'account': account,
'password': password, 'cookie': cookie}
db.Cookies.insert_one(item)
cookies.append(cookie)
print "*******************************"
print "Get Cookie Successful: %s!!!!!!" % account
print "*******************************"
continue
print "*******************************"
print "Get Cookie Failed: %s!" % account
print "*******************************"
except Exception, e:
print "*******************************"
print "%s Failure!!!!!" % account
print e
print "*******************************"
finally:
def run_server():
global db
db = MongoDB()
run(host=host, port=port)
db.clear_db()
# data['临床表现'] = data['临床表现'].str.replace(r'等.*?(?:\s|$)|[，。,.、；;]', ' ')
# data['临床表现'] = data['临床表现'].str.replace(r'或|常伴|伴有?|发生|[轻甚]则|甚至', '')
# data['临床表现'] = data['临床表现'].str.replace(r'[^\s]{9,}', ' ')
# data['临床表现'] = data['临床表现'].str.replace(r'\s+', ' ')
data['临床表现'] = data['临床表现'].str.strip()
data.drop_duplicates('病证', 'last', inplace=True)
# data = data['临床表现'].str.split().tolist()
# data = [j for i in data for j in i]
# counter = Counter(data)
# print(data['临床表现'])
# data.to_excel('bz2.xls', index=False)
# bz = pd.read_excel('bz.xls')[['病症', '临床表现']]
mongo = MongoDB()
food_info = mongo.find_all('diet_merge', projection={'name': 1, 'ingredients': 1, 'syndrome': 1})
food_info_df = pd.DataFrame(data=[[f['name'], f['ingredients'], f['syndrome']] for f in food_info], columns=['食疗方', '食材', '主治'])
food_info_df['存在关联'] = 0
food_info_df['主治'] = food_info_df['主治'].str.replace('证', '').str.replace('型', '')
food_info_df.loc[food_info_df['主治'] != '', '主治'] = food_info_df['主治'] + '证'
food_bz = [item['syndrome'] for item in food_info]
food_bz = list(filter(None, food_bz))
print('Food(Total): {}'.format(len(food_bz)))
food_bz = set([item.replace('证', '').replace('型', '') for item in food_bz])
results = []
n_valid_bz = 0
valid_bz_set = set()
for item in food_bz:
from core import PastePwn
from scraping.pastebin import PastebinScraper
from database import MongoDB
logdir_path = os.path.dirname(os.path.abspath(__file__))
logfile_path = os.path.join(logdir_path, "logs", "pastepwn.log")
if not os.path.exists(os.path.join(logdir_path, "logs")):
os.makedirs(os.path.join(logdir_path, "logs"))
logfile_handler = logging.handlers.WatchedFileHandler(logfile_path, "a", "utf-8")
logger = logging.getLogger(__name__)
logging.basicConfig(format="%(asctime)s - %(name)s - %(levelname)s - %(message)s", level=logging.DEBUG, handlers=[logfile_handler, logging.StreamHandler()])
# Framework code
database = MongoDB(ip="192.168.240.128")
pastepwn = PastePwn(database)
pastepwn.add_scraper(PastebinScraper())
telegram_action = TelegramAction(token="token", receiver="-1001348376474")
mail_analyzer = MailAnalyzer(telegram_action)
premium_analyzer = WordAnalyzer(telegram_action, "premium")
pastepwn.add_analyzer(mail_analyzer)
pastepwn.add_analyzer(premium_analyzer)
pastepwn.start()
def drop_coupon_table(self):
MongoDB().drop_coupon_collection()
# -*- coding: utf-8 -*-
from database import MongoDB
import check, os
from telegram.ext import Updater, CommandHandler, MessageHandler, Filters
Token = "376593798:AAHMNABESGpXiFGiQ8Bg-0CnHc2EwyXD1hk"
updater = Updater(token=Token)
dispatcher = updater.dispatcher
mongodb = MongoDB()
admins = ["utkucanbykl", "vlademir92", "badgeekluck"]
users = ["utkucanbykl", "vlademir92", "badgeekluck"]
def start(bot, update):
bot.sendMessage(chat_id=update.message.chat_id, text="Bot çalışıyor.")
def hello(bot, update):
bot.sendMessage(chat_id=update.message.chat_id,
text="Hello " + update.message.from_user.first_name)
def echo(bot, update):
class getnews(object):
def __init__(self):
self.mongo = MongoDB()
self.news_url_queue = news_url_Queue() # 存新闻url，用于多线程爬取
self.news_html_queue = news_url_Queue() # 存新闻html
self.old_day_news_queue = news_url_Queue()
# self.log = Logging('../helloword/static/sina').get_logging()
self.log = Logging('../Sina/sina.txt').get_logging()
def run(self, nums):
#开始计时，爬完一次需用时
time_0 = time.time()
#获取当天所有新闻url，加入news_url_queue
self.get_news_url()
time.sleep(5)
#将数据库里以前的url信息读取到old_day_news_queue
self.read_url_info()
#开始逐个判断old_day_news_queue里的评论是否有更新，有则加入news_url_queue，否则就删除数据库本地信息，直到队列空
thread_list3 = [
threading.Thread(target=self.judge_comment) for i in range(nums)
]
for t in thread_list3:
t.start()
for t in thread_list3:
if t.is_alive():
t.join()
time.sleep(5)
#去除重复元素
xqueue = set(self.news_url_queue.queue)
self.news_url_queue.queue = list(xqueue)
#逐个读取news_url_queue内容，获取正文html，并存入news_html_queue，直到队列空
thread_list = [
threading.Thread(target=self.get_news_html) for i in range(nums)
]
for t in thread_list:
t.start()
for t in thread_list:
if t.is_alive():
t.join()
time.sleep(5)
print '新闻个数： ' + str(len(self.news_html_queue.queue))
#开始逐个解析news_html_queue里的内容，同时存正文，爬评论存评论，存url信息到数据库，直到队列空
thread_list2 = [
threading.Thread(target=self.get_message) for i in range(nums)
]
for x in thread_list2:
x.start()
for x in thread_list2:
if x.is_alive():
x.join()
print("结束: ", time.time() - time_0, "\n")
def get_news_url(self):
URL_LIST = [
'http://news.sina.com.cn/society/', 'http://ent.sina.com.cn/',
'http://sports.sina.com.cn/', 'http://finance.sina.com.cn/',
'http://news.sina.com.cn/china/'
]
re_list = [
'http://news.sina.com.cn/[a-z]+/[a-z]+/\d{4}-\d{2}-\d{2}/doc-[a-z]{8}\d{7}.shtml',
'http://ent.sina.com.cn/[a-z]+/[a-z]+/\d{4}-\d{2}-\d{2}/doc-[a-z]{8}\d{7}.shtml',
'http://sports.sina.com.cn/[a-z]+/[a-z]+/\d{4}-\d{2}-\d{2}/doc-[a-z]{8}\d{7}.shtml',
'http://finance.sina.com.cn/[a-z]+/[a-z]+/\d{4}-\d{2}-\d{2}/doc-[a-z]{8}\d{7}.shtml',
'http://news.sina.com.cn/[a-z]+/[a-z]+/\d{4}-\d{2}-\d{2}/doc-[a-z]{8}\d{7}.shtml'
]
time_today = time.strftime("%Y-%m-%d", time.localtime(time.time()))
for channel in range(0, 5):
URL = URL_LIST[channel]
while 1:
print '新闻版块： ' + URL
try:
html = requests.get(URL, timeout=30).content
break
except Exception as e:
self.log.info(
'can not get the source page for news urllist')
# print e
re_ = re_list[channel]
news_url_list = re.findall(re_, html)
print '本版块个数： ' + str(len(news_url_list))
for j in news_url_list:
this_time = re.search('\d{4}-\d{2}-\d{2}', j).group(0)
if this_time == time_today:
self.news_url_queue.queue.append(j)
else:
pass
def read_url_info(self):
try:
self.old_day_news_queue.queue = self.mongo.get_urls()
except Exception as e:
self.log.info('function read_url_info() error!')
self.log.info(e)
def judge_comment(self):
while len(self.old_day_news_queue.queue):
try:
info = self.old_day_news_queue.out_queue()
url = info['_id']
comment_count = self.getCommentNumber(url)
flag = comment_count - info['comment_count']
if flag >= 20:
self.news_url_queue.queue.append(url)
else:
self.mongo.delete_url(url)
except Exception as e:
self.log.info('function judge_comment() error')
self.log.info(e)
def get_news_html(self):
while len(self.news_url_queue.queue):
i = self.news_url_queue.out_queue()
try:
html = requests.get(i, timeout=30).content.decode()
# print i
self.news_html_queue.in_queue(html)
except Exception as e:
self.log.info('can not get this page of html' + i)
self.log.info(e)
def get_message(self):
while len(self.news_html_queue.queue):
try:
i = self.news_html_queue.out_queue()
#排除手机版网页
if re.findall(r'<meta property="og:url" content="(.*?)" />',
i):
news_url = re.findall(
r'<meta property="og:url" content="(.*?)" />', i)[0]
else:
continue
ping_lun_shu_liang = self.getCommentNumber(news_url)
yue_du_shu = None
if ping_lun_shu_liang:
all_page = ping_lun_shu_liang / 20
comment_url_list = []
for page in xrange(1, all_page + 1):
newsid = re.findall(r'([a-z]{7}\d{7})\.shtml',
news_url)[0]
channel = re.findall(r'http://(.*?).sina', news_url)[0]
if (channel == 'finance'):
channel = 'cj'
elif (channel == 'sports'):
channel = 'ty'
elif (channel == 'ent'):
channel = 'yl'
else:
channel = re.findall(r'com\.cn/([a-z]+)/',
news_url)[0]
if (channel == 's'):
channel = 'sh'
else:
channel = 'gn'
comment_url = 'http://comment5.news.sina.com.cn/page/info?format=js&channel=%s&newsid=comos-%s&group=&compress=1&ie=gbk&oe=gbk&page=%s&page_size=20' % (
channel, newsid, page)
comment_url_list.append(comment_url)
for com_url in comment_url_list:
self.get_comment(news_url, com_url)
else:
ping_lun_shu_liang = 0
tree = etree.HTML(i)
message_dict = dict()
url_info = dict()
# print' 文章网址'
wen_zhang_wang_zhi = news_url
message_dict['wen_zhang_wang_zhi'] = wen_zhang_wang_zhi
# print' # 文章标题'
wen_zhang_biao_ti = pathOneNode(
tree, '//div[@class="main-content w1240"]/h1/text()')
message_dict['wen_zhang_biao_ti'] = wen_zhang_biao_ti
# print' # 发布时间'
fa_bu_shi_jian = pathOneNode(
tree, '//div[@class="date-source"]/span/text()')
if not fa_bu_shi_jian:
fa_bu_shi_jian = re.findall(
'<span class="titer">(.*?)</span>', i)[0]
fa_bu_shi_jian = re.findall('(\d{4}.*\d{2})',
fa_bu_shi_jian)[0]
# print news_url+fa_bu_shi_jian
message_dict['fa_bu_shi_jian'] = fa_bu_shi_jian
# print' # 评论数量'
ping_lun_shu_liang = ping_lun_shu_liang
message_dict['ping_lun_shu_liang'] = ping_lun_shu_liang
# print' # 文章来源'
# (//div[@class="article article_16"]/p[2]/text())
wen_zhang_lai_yuan = pathOneNode(
tree,
'//div[@class="date-source"]/a/text()| //div[@class="date-source"]/span[@class="source ent-source"]/text()|//div[@class="date-source"]/span[@class="source"]/text()'
)
message_dict['wen_zhang_lai_yuan'] = wen_zhang_lai_yuan
# print' # 文章正文'
wen_zhang_zheng_wen = tree.xpath(
'//div[@class="article"]/p/text()')
wen_zhang_zheng_wen = ''.join(wen_zhang_zheng_wen)
#print wen_zhang_zheng_wen
message_dict['wen_zhang_zheng_wen'] = wen_zhang_zheng_wen
# print' # 抓取时间'
do_time = time.time()
message_dict['do_time'] = do_time
# print' # 抓取网站'
zhan_dian = u'新浪网'
message_dict['zhan_dian'] = zhan_dian
# print' # 图片链接'
tu_pian_lian_jie = tree.xpath(
'//div[@class="img_wrapper"]/img/@src')
if tu_pian_lian_jie:
tu_pian_lian_jie = ' '.join(tu_pian_lian_jie)
if tu_pian_lian_jie.startswith('http:'):
tu_pian_lian_jie = tu_pian_lian_jie
else:
tu_pian_lian_jie = 'http:' + tu_pian_lian_jie
message_dict['tu_pian_lian_jie'] = tu_pian_lian_jie
else:
message_dict['tu_pian_lian_jie'] = None
# print' # 文章栏目'
# wen_zhang_lan_mu = pathAllNode(tree,
# '(//div[@class="bread"]/a)|(//div[@class="bread"]/span)|(//div[@class="nav-g__breadcrumb layout-fl"]/a)|(//div[@class="text notInPad"]/a)')
# message_dict['wen_zhang_lan_mu'] = wen_zhang_lan_mu
#
# print' # 文章作者'
if tree.xpath(
'(//p[@class="article-editor"]/text())|(//p[@class="show_author"]/text())'
):
wen_zhang_zuo_zhe = pathOneNode(
tree,
'(//p[@class="article-editor"]/text())|(//p[@class="show_author"]/text())'
)
else:
wen_zhang_zuo_zhe = '佚名'
message_dict['wen_zhang_zuo_zhe'] = wen_zhang_zuo_zhe
# print' # 关键词'
if tree.xpath('//div[@class="keywords"]'):
guan_jian_ci = tree.xpath(
'//div[@class="keywords"]/a/text()')
guan_jian_ci = ' '.join(guan_jian_ci)
else:
guan_jian_ci = None
message_dict['guan_jian_ci'] = guan_jian_ci
# print' # 相关标签'
# xiang_guan_biao_qian = pathAllNode(tree,'(//section[@class="article-a_keywords"])|(//p[@class="art_keywords"])')
# message_dict['xiang_guan_biao_qian'] = xiang_guan_biao_qian
#
# print' # 阅读数量'
yue_du_shu = yue_du_shu
message_dict['yue_du_shu'] = yue_du_shu
# print' # 主键'
message_dict['_id'] = news_url
# print json.dumps(message_dict, ensure_ascii=False, indent=4)
print '剩余未爬取新闻个数' + str(len(self.news_html_queue.queue))
url_info['_id'] = news_url
url_info['comment_count'] = ping_lun_shu_liang
url_info['do_time'] = do_time
self.mongo.put_url(url_info)
self.mongo.put_content(message_dict)
except Exception as e:
self.log.info(e)
# print e
def getCommentNumber(self, news_url):
newsid = re.findall(r'([a-z]{7}\d{7})\.shtml', news_url)[0]
channel = re.findall(r'http://(.*?).sina', news_url)[0]
if (channel == 'finance'):
channel = 'cj'
elif (channel == 'sports'):
channel = 'ty'
elif (channel == 'ent'):
channel = 'yl'
else:
channel = re.findall(r'com\.cn/([a-z]+)/', news_url)[0]
if (channel == 's'):
channel = 'sh'
else:
channel = 'gn'
comment_url = 'http://comment5.news.sina.com.cn/page/info?version=1&format=js&channel=%s&newsid=comos-%s&group=&compress=0&ie=utf-8&oe=utf-8&page=1&page_size=20' % (
channel, newsid)
flag = 1
while 1:
try:
x = requests.get(comment_url, timeout=30).content
# print x
json_object = json.loads(
re.findall('var data=([\S\s]+)', x)[0])
break
except Exception as e:
flag += 1
self.log.info('default to get this page of comment')
# print e
if flag > 5:
return
# 阅读数
# yue_du_shu = json_object['join_count']
# 评论数
try:
ping_lun_shu_liang = json_object['result']['count']['show']
except Exception as e:
ping_lun_shu_liang = 0
#return yue_du_shu
return ping_lun_shu_liang
def get_comment(self, news_url, comment_url):
# print '开始获取评论'
try:
# print comment_url
json_object = json.loads(
requests.get(comment_url,
timeout=30).content.replace('var data=', ''))
# print json_object
comment_dict = dict()
for item in json_object['result']['cmntlist']:
# 评论文章url
news_url = news_url
# 评论内容
ping_lun_nei_rong = item["content"]
comment_dict['ping_lun_nei_rong'] = ping_lun_nei_rong
# 评论时间
ping_lun_shi_jian = item["time"]
comment_dict['ping_lun_shi_jian'] = ping_lun_shi_jian
# 回复数量
hui_fu_shu = None
comment_dict['hui_fu_shu'] = hui_fu_shu
# 点赞数量
dian_zan_shu = item["agree"]
comment_dict['dian_zan_shu'] = dian_zan_shu
# 评论id
ping_lun_id = item["mid"]
comment_dict['ping_lun_id'] = ping_lun_id
# 用户昵称
yong_hu_ming = item["nick"]
comment_dict['yong_hu_ming'] = yong_hu_ming
# 性别
xing_bie = None
comment_dict['xing_bie'] = xing_bie
# 用户等级
yong_hu_deng_ji = item["level"]
comment_dict['yong_hu_deng_ji'] = yong_hu_deng_ji
# 用户省份
yong_hu_sheng_fen = item["area"]
comment_dict['yong_hu_sheng_fen'] = yong_hu_sheng_fen
# 抓取时间
do_time = time.time()
comment_dict['do_time'] = do_time
# 抓取网站
zhan_dian = u'新浪'
comment_dict['zhan_dian'] = zhan_dian
# 主键
comment_dict['_id'] = ping_lun_id + news_url
# print json.dumps(comment_dict, ensure_ascii=False, indent=4)
self.mongo.put_comment(comment_dict)
except Exception as e:
self.log.info(e)
