Code: Alles auswählen
soup = BeautifulSoup (urlopen("http://localhost/m.html"))
result1 = soup.find_all('li', {'class': 'lvgrad'})
print (result1)Code: Alles auswählen
<li class="lvgrad prc">
<span class="bold">
<b>Grad</b> 33,59</span></li>Als Antwort bekomme?Grad; 33,59
Code: Alles auswählen
from bs4 import BeautifulSoup
html = """<body><li class="lvgrad prc">
<span class="bold">
<b>Grad</b> 33,59</span></li></body>"""
soup = BeautifulSoup(html, "html.parser")
results = soup.find_all("li", {"class": "lvgrad"})
for result in results:
print([result.get_text()]) # Angucken der Lieferung
print(result.get_text().strip("\n"))
Code: Alles auswählen
soup = BeautifulSoup (urlopen("http://localhost/m.html"), "html.parser")
f = csv.writer(open("test.csv", "w"))
f.writerow(["Grad","Format","Datum"])
result1 = soup.find_all("li", {"class": "lvgrad"})
for result_back_one in result1:
one = result_back_one.get_text().strip()
one_new = one.replace('Grad', 'Grad;')
print([one_new])
result2 = soup.find_all("li", {"class": "lvformat"})
for result_back_two in result2:
two = result_back_two.get_text().strip()
print([two])
result3 = soup.find_all("li", {"class": "lvdate"})
for result_back_three in result3:
three = result_back_three.get_text().strip()
print([three_new])
f.writerow([one_new, two, three_new])Code: Alles auswählen
<li fid="4243b1c99" _sp="p2046732.m1686.l1" Id="531698" class="sresult lvresult clearfix li shic" r="2" >
<li class="lvgrad"><span class="bold"><b>Grad</b>38,49</span>
</li>
<li class="lvformat"><span >MEZ</span>
</li>
<li class="lvdate"><span class="date">05-02-2016</span>
</li>
</ul>
</li>
Code: Alles auswählen
# coding: utf-8
import csv
from bs4 import BeautifulSoup
from urllib.request import urlopen
soup = BeautifulSoup (urlopen("http://localhost/m.html"), "html.parser")
f = csv.writer(open("test.csv", "w", newline=''))
f.writerow(["Grad","Format","Datum"])
result1 = soup.find_all("li", {"class": "lvgrad"})
for result_back_one in result1:
one = result_back_one.get_text().strip()
one_new = one.replace('Grad', 'Grad;')
print([one_new])
result2 = soup.find_all("li", {"class": "lvformat"})
for result_back_two in result2:
two = result_back_two.get_text().strip()
print([two])
result3 = soup.find_all("li", {"class": "lvdate"})
for result_back_three in result3:
three = result_back_three.get_text().strip()
print([three_new])
f.writerow([one_new, two, three_new])
Heute nicht mehr. Und Jein, das was ich mache kann man nicht programmieren nennen. Ich habe mich eine Zeit lang mit html und c++ beschäfftigt, aber nie wirklich auf einem stand der es mir ermöglicht hätte ohne google auszukommen. Seit ca. 6 Jahren habe ich garnichts mehr gemacht und nun mache ich meine ersten Versuche mit Python.pixewakb hat geschrieben: BTW: Lies das Tutorial und arbeite es durch, ich habe aber irgendwie bei dir den Eindruck, dass Du schon länger programmierst.
Code: Alles auswählen
# coding: utf-8
import csv
from bs4 import BeautifulSoup
from urllib.request import urlopen
# Dein HTML-Code ist kaputt!?
html_code = """
<ul>
<li fid="4243b1c99" _sp="p2046732.m1686.l1" Id="531698" class="sresult lvresult clearfix li shic" r="2" ></li>
<li class="lvgrad"><span class="bold"><b>Grad</b>38,49</span></li>
<li class="lvformat"><span >MEZ</span></li>
<li class="lvdate"><span class="date">05-02-2016</span></li>
</ul>
<ul>
<li fid="4243b1c99" _sp="p2046732.m1686.l1" Id="531699" class="sresult lvresult clearfix li shic" r="2" ></li>
<li class="lvgrad"><span class="bold"><b>Grad</b>39,51</span></li>
<li class="lvformat"><span >MEZ</span></li>
<li class="lvdate"><span class="date">06-02-2016</span></li>
</ul>"""
soup = BeautifulSoup (html_code, "html.parser")
list_id = []
list_temp = []
list_format = []
list_datum = []
# Daten auslesen
results0 = soup.find_all("li", {"class": "lvresult"})
# print([results0])
for result_back_one in results0:
zero = result_back_one
list_id.append(zero.get('id'))
results1 = soup.find_all("li", {"class": "lvgrad"})
# print([results1])
for result_back_one in results1:
one = result_back_one.get_text().strip()
one_new = one.replace('Grad',"")
list_temp.append(one_new)
results2 = soup.find_all("li", {"class": "lvformat"})
for result_back_two in results2:
two = result_back_two.get_text().strip()
list_format.append(two)
result3 = soup.find_all("li", {"class": "lvdate"})
for result_back_three in result3:
three = result_back_three.get_text().strip()
list_datum.append(three)
# Ausgabe
with open('test.csv', 'w') as csvfile:
resultwriter = csv.writer(csvfile,
delimiter=';',
lineterminator='\n',
quotechar='|',
quoting=csv.QUOTE_MINIMAL)
resultwriter.writerow(["ID", "Grad", "Format", "Datum"])
for i, value in enumerate(list_id):
resultwriter.writerow([value, list_temp[i], list_format[i], list_datum[i]])
Code: Alles auswählen
# coding: utf-8
import csv
import xlsxwriter
from bs4 import BeautifulSoup
from urllib.request import urlopen
urlpfad = ("april-2015")
soup = BeautifulSoup (urlopen("http://www.xyz.de/"+urlpfad.rstrip()+"/m.html"), "html.parser")
list_id = []
list_temp = []
list_format = []
list_datum = []
#start scrapping de
results0 = soup.find_all("li", {"class": "lvresult"})
# print([results0])
for result_back_one in results0:
zero_de = result_back_one
list_id.append(zero_de.get('id'))
#print (list_id_de)
result1
...
try:
result2
...
except Exception:
pass
result3
...
#Ausgabe xlsx
workbook = xlsxwriter.Workbook(urlpfad+'.xlsx')
worksheet = workbook.add_worksheet("Sheet1")
index = 1
for entry in list_id:
worksheet.write_string(index, 0, entry)
index = index + 1
index = 1
for entry in list_temp:
worksheet.write_string(index, 1, entry)
index = index + 1
index = 1
for entry in list_format:
worksheet.write_string(index, 2, entry)
index = index + 1
index = 1
for entry in list_datum:
worksheet.write_string(index, 3, entry)
index = index + 1
print(urlpfad+'.xlsx wurde erstellt')
workbook.close()
Code: Alles auswählen
fileobject = open("test-import.txt")
for urlpfad in fileobject:
print (urlpfad.rstrip())
fileobject.close()
for ergebnis in urlpfad:
if ergebnis == "EoF":
break
print(ergebnis)
else:
print("Keine weiteren Pfade")
print("Finish")