我正在废止一个网站的一些列表,并设法让大部分功能工作,除了废止描述。
这里是一个广告的URL。https:/eg.hatla2ee.comencarhondacivic3289785。
这是我的代码。
for link in df['New Carlist Unit 1_link']:
url = requests.get(link)
soup = BeautifulSoup(url.text, 'html.parser')
### Get title
title =[]
try:
title.append(soup.find('h1').text.strip())
except Exception as e:
None
## Get price
price = []
try:
price.append(soup.find('span',class_="usedUnitCarPrice").text.strip())
except Exception as e:
None
##Get Description box
label =[]
text =[]
try:
for span in soup.find_all('span',class_="DescDataSubTit"):
label.append(span.text.strip())
text.append(span.find_next_sibling().text.strip())
except Exception as e:
None
print('*'*100)
print(title)
print(price)
print(label)
print(text)
time.sleep(1)
由于某些原因,我似乎无法收集所有的span标签。
这是我想要的输出。
{'Make': 'Honda'}
{'Model': 'Crosstour'}
{'Used since': '2012'}
{'Km': '0 Km'}
{'Transmission': 'automatic'}
{'City': 'Cairo'}
{'Color': 'Gold'}
{'Fuel': 'gas'}
import requests
from bs4 import BeautifulSoup
def main(url):
r = requests.get(url)
soup = BeautifulSoup(r.content, 'html.parser')
target = soup.select_one("div.DescDataRow").select("span.DescDataSubTit")
for tar in target:
g = {tar.text: tar.find_next("span").get_text(strip=True)}
print(g)
main("https://eg.hatla2ee.com/en/car/honda/civic/3289785")
输出。
{'Make': 'Honda'}
{'Model': 'Civic'}
{'Used since': '1990'}
{'Km': '1,500 Km'}
{'Transmission': 'automatic'}
{'City': 'Port Said'}
{'Color': 'Dark red'}
{'Fuel': 'gas'}
import requests
from bs4 import BeautifulSoup
def main(url):
r = requests.get(url)
soup = BeautifulSoup(r.content, 'html.parser')
target = [list(item.stripped_strings)
for item in soup.select("div.DescDataContain")][0][:16]
print(dict(zip(*[iter(target)]*2)))
main("https://eg.hatla2ee.com/en/car/honda/civic/3289785")
输出:
{'Make': 'Honda', 'Model': 'Civic', 'Used since': '1990', 'Km': '1,500 Km', 'Transmission': 'automatic', 'City': 'Port Said', 'Color': 'Dark red', 'Fuel': 'gas'}