def parse(pageString):
result = {}
bsObj = BeautifulSoup(pageString, "html.parser")
# print(bsObj)
qtDayText2 = bsObj.find("div", {"id": "qtDay"})
try:
extDat = findMatchedTexts(qtDayText2.text, "201[\s\S]+")
ss = extDat[0].split("\r\n ")
ss2 = "{} {}".format(ss[0].replace("\n", ". "), ss[1])
result['date'] = ss2
res = findMatchedTexts(qtDayText2.text, "\(.+\)")
result['addr'] = getAddr(res[0])
except Exception as e:
print(e)
box2Content = bsObj.find("div", {"class": "box2Content"})
result['box2Content'] = box2Content.text
# result['srcipt'] = script.text
content = bsObj.find("div", {"id": "content"})
ps = content.findAll("p")
result['content'] = ps[4].text
bx2 = bsObj.find("div", {"class": "bx2"})
guideText = bx2.text
result['bx2'] = addLine(guideText)
return result
def get_row(tr):
tds = tr.find_all('td')
atag = str(tds[0].find('a')).split('<span class="tit_info">')
first = ''
try:
first = re.compile('\t.*\t').sub('', atag[0]).split('\n')[1]
first = first.replace('R&amp;amp;amp;D ', '')
except:
print('----------')
second = ''
try:
second = atag[1].split('</span>')[0]
second = second.replace('R&amp;D ', '')
except:
print('---------')
# print(tds[1], tds[2], tds[3])
api_id = ''
try:
id_a = tds[0].find('h4').find('a')['href']
api_id = findMatchedTexts(id_a, "javascript:view\('[0-9]+")[0]
api_id = api_id.replace("javascript:view('", "")
except Exception as e:
print('----api id exception -----')
service_types = []
try:
service_types_spans = tds[5].find('div', {
'class': 'datatype'
}).find_all('span')
service_types = [span.text for span in service_types_spans]
except Exception as e:
print('----- serivce types exception -------')
return {
'api_id': api_id,
'title': first,
'subtitle': second,
'count': tds[3].text,
'service_types': service_types
}
from libs.crawler import crawl
from bs4 import BeautifulSoup
from libs.patternMatcher import findMatchedTexts
url = "http://dart.fss.or.kr/corp/searchAutoComplete.do?textCrpNm=%EC%85%80%ED%8A%B8%EB%A6%AC%EC%98%A8&_=1561171426973"
pageString = crawl(url)
bsObj = BeautifulSoup(pageString, "html.parser")
names = findMatchedTexts(bsObj.text, "셀트리온[가-힣0-9a-zA-z]*")
print(names)
for name in names:
print(name)