Vous pouvez utiliser:
path = 'C:/Users/.../.../output/'
#read html files
for filename in glob.glob(os.path.join(path, '*.html')):
soup = bs4.BeautifulSoup(open(filename).read(), "lxml")
title = soup.find('h1')
ticker = soup.find('p')
d_date = soup.find_all('div', {"id": "a-body"})[0].find_all("p")[2]
try:
def find_participant(tag):
return tag.name == 'p' and tag.find("strong", text=re.compile(r"Executives|Corporate Participants"))
participants = soup.find(find_participant)
parti_names = ""
for parti in participants.find_next_siblings("p"):
if parti.find("strong", text=re.compile(r"(Operator)")):
break
parti_names += parti.get_text(strip=True) + ","
except:
indexFile = open('C:/Users/.../output1/' + 'index.txt', 'a+')
indexFile.write(filename + ', ' + title.get_text(strip=True) + ', '+ ticker.get_text(strip=True) + ', ' + d_date.get_text(strip=True) + ', ' + 'No participants' + '\n')
else:
participants = soup.find(find_participant)
parti_names = ""
for parti in participants.find_next_siblings("p"):
if parti.find("strong", text=re.compile(r"(Operator)")):
break
parti_names += parti.get_text(strip=True) + ","
indexFile = open('C:/Users/.../output1/' + 'index.txt', 'a+')
indexFile.write(os.path.basename(filename) + ', ' + title.get_text(strip=True) + ', '+ ticker.get_text(strip=True) + ', ' + d_date.get_text(strip=True) + ', ' + parti_names + '\n')
indexFile.close()
comment puis-je l'appliquer à mon code? –
J'ai ajouté comment l'utiliser –
pour le nom de fichier dans glob.glob (os.path.join (chemin, '* .html')): print os.path.basename (filename) –