def f():
tbl = mongo1.db['뉴스_ETRI언어분석_원본']
etri = models.ETRIAI('WiseNLU', 'srl')
docids = etri.distinct(key='docid',
filter={
'colname': 'bodytext',
'results': None
})
loop = dbg.Loop('뉴스_ETRI언어분석_원본', len(docids))
for docid in docids:
cursor = tbl.find({'뉴스id': docid}, {
'_id': 0,
'뉴스id': 1,
'뉴스본문srl_res': 1
})
docs = list(cursor)
if len(docs) is 1:
d = docs[0]
etri.modelnm = 'Article__네이버_모바일홈'
etri.docid = d['뉴스id']
etri.colname = 'bodytext'
etri.results = d['뉴스본문srl_res']
etri.update_doc(
{
'modelnm': etri.modelnm,
'docid': etri.docid,
'colname': etri.colname
}, True)
loop.report()
def collect():
self = Assemblymen()
party = Party().get()
loop = dbg.Loop(f"{self.__class__} | {inspect.stack()[0][3]}", len(party))
for d in party.to_dict('records'):
party.attributize(d)
self.collect(party.name, party.code).parse()
loop.report(addi_info=f" partyname : {party.name}")
def parse(self):
loop = dbg.Loop(f"{self.__class__} | {inspect.stack()[0][3]}",
len(self.docs))
for d in self.docs:
self.attributize(d)
lay = MobileNewsHomeLayoutParser(self.html, self.pageuri)
self.layout = lay.parse().docs
self.update_doc({'_id': self._id}, True)
loop.report(addi_info=f" snapshot_dt : {self.snapshot_dt}")
return self
def collect():
page = models.NewsPage()
page.load()
loop = dbg.Loop(
f"{sys.modules[__name__].__file__} | {inspect.stack()[0][3]}",
len(page.docs))
for d in page.docs:
page.attributize(d)
ss = SnapshotCollector(page.pressname, page.name, page.url)
ss.collect()
loop.report(addi_info=page.url)
def collect(pressname=None, pagename=None):
fr = dbg.Function(inspect.currentframe()).report_init()
filter = {}
if isinstance(pressname, str) and isinstance(pagename, str):
filter.update({'pressname': pressname, 'name': pagename})
page = models.NewsPage().load(filter)
loop = dbg.Loop(
f"{sys.modules[__name__].__file__} | {inspect.stack()[0][3]}",
len(page.docs))
for d in page.docs:
page.attributize(d)
c = Collector(page.pressname, page.name)
c.collect()
loop.report(
addi_info=f" pressname : {page.pressname}, pagename : {page.name}")
fr.report_fin()
def parse(self):
loop = dbg.Loop(f"{self.__class__} | {inspect.stack()[0][3]}",
len(self.docs))
for d in self.docs:
self.attributize(d)
soup = BeautifulSoup(d['html'], 'html.parser')
self.detect_right_panel(soup)
self.top_card()
self.job_summary()
self.job_description()
self.how_you_match()
self.competitive_intelligence_about_applicants()
self.insight_look_at_company()
self.commute()
self.about_us()
self.update_doc({'_id': d['_id']}, False)
# break
loop.report()
def collect(self):
self.get_targets()
if hasattr(self, 'article'):
article = copy.copy(self.article)
loop = dbg.Loop(f"{self.__class__} | {inspect.stack()[0][3]}",
len(article.docs))
for d in article.docs:
article.attributize(d)
self.docid = article._id
jsondata = self.etriapi.api(
text=getattr(article, self.targetcol))
if isinstance(jsondata, dict):
self.results = [jsondata]
self.update_doc({'docid': self.docid}, True)
loop.report(
addi_info=
f" 기사 {self.targetcol} 일부 : {getattr(article, self.targetcol)[:30]}"
)
def collect(self):
target_urls = self.get_targets()
if target_urls is not None:
loop = dbg.Loop(f"{self.__class__} | {inspect.stack()[0][3]}",
len(target_urls))
for url in target_urls:
self.url = url
try:
r = requests.get(self.url)
except Exception as e:
print(f"\n Exception :\n{e}\n")
else:
if (r.status_code is 200) and (len(r.text) is not 0):
self.html = r.text
self.update_doc({'url': self.url}, True)
else:
print(f"\n{'#'*60}\n 네이버에서 이상감지를 한 듯.")
dbg.obj(r,
f"{self.__class__} | {inspect.stack()[0][3]}")
loop.report(addi_info=f" url : {self.url}")
def parse(self):
self.get_targets()
loop = dbg.Loop(f"{self.__class__} | {inspect.stack()[0][3]}",
len(self.docs))
for d in self.docs:
self.attributize(d)
soup = BeautifulSoup(self.html, 'html.parser')
s = soup.find('div', class_='responsive_col1')
if s is None:
errmsg = f"soup.find('div',class_='responsive_col1') is None.\n 기사페이지의 핵심내용태그(responsive_col1)가 없는 껍데기 페이지."
print(
f"\n{'#'*60}\n{self.__class__} | {inspect.stack()[0][3]}\n {errmsg}"
)
else:
self.parse_uppertier(s)
self.parse_middletier(s)
self.parse_lowertier(s)
if len(list(self.schematize().doc)) > 3:
self.update_doc({'_id': self._id})
loop.report(addi_info=self.url)
def divide_NewsPageSnapshot():
tbl = mongo.db['NewsPageSnapshot']
"""url별로 작업하기 위해 urls 리스트 로딩."""
page = models.NewsPage()
page.load()
loop = dbg.Loop('divide_NewsPageSnapshot', len(page.docs))
for d in page.docs:
"""pageid에 해당하는 snapshot 데이터 로딩."""
page.attributize(d)
cursor = tbl.find({'pageid': page._id}, {
'_id': 0,
'collect_dt': 1,
'html': 1
})
"""newspage마다 테이블로 분할된 데이터모델에 로딩한 데이터를 저장."""
ss = models.NewsPageSnapshot(page.pressname, page.name)
ss.docs = list(cursor)
for d in ss.docs:
ss.attributize(d)
ss.update_doc({'collect_dt': ss.collect_dt}, True)
loop.report(addi_info=page.url)
def migrate_screen_tbl():
"""url별로 작업하기 위해 urls 리스트 로딩."""
tbl = mongo1.db['screen']
urls = tbl.distinct(key='url')
loop = dbg.Loop('migrate_screen_tbl', len(urls))
for url in urls:
"""url에 해당하는 pageid를 검색."""
page = models.NewsPage().load({'url': url})
if len(page.docs) is 1:
page.attributize(page.docs[0])
"""screen-tbl에서 마이그할 대상 문서로딩."""
cursor = tbl.find({'url': url}, {'_id': 0})
scrdf = pd.DataFrame(list(cursor))
cols_map = {'r_txt': 'html', '수집일시': 'collect_dt'}
scrdf = scrdf.rename(columns=cols_map).reindex(
columns=['html', 'collect_dt'])
"""Snapshot-tbl에 마이그."""
ss = models.NewsPageSnapshot(page.pressname, page.name)
ss.docs = scrdf.to_dict('records')
for d in ss.docs:
ss.attributize(d)
ss.update_doc({'collect_dt': ss.collect_dt}, True)
loop.report(addi_info=url)
def collect_1page(sleepsecs=10):
"""url 하나당 25개의 Job-postings 를 수집/파싱한다.
리스트를 반복하며 Job Posting 상세내용을 수집-분석.
"""
fr = dbg.Function(inspect.currentframe()).report_init()
uo = urlparse(driver.current_url)
if ('keywords' in uo.query) and ('location' in uo.query):
# jobcards = driver.find_elements_by_class_name('occludable-update')
jobcards = driver.find_elements_by_class_name('artdeco-list__item')
collect_dt = datetime.today().astimezone()
loop = dbg.Loop(f"{inspect.stack()[0][3]} | jobcard-index progress",
len(jobcards))
for i, jobcard in enumerate(jobcards):
time.sleep(sleepsecs)
############################################################
jobcard_job_details(jobcard)
############################################################
loop.report()
fr.report_fin()
else:
print(
f"\n keywords와 locations이 url에 없다.\n driver.current_url : {driver.current_url}"
)
time.sleep(sleepsecs)
