对于方法中的搜索买家,我需要获取该买家的价格
def getprice(search_buyer):
try:
# webscrape url
url = 'http://econpy.pythonanywhere.com/ex/001.html'
response = requests.get(url)
print(response)
tree = html.fromstring(response.content)
buyers = tree.xpath('//div[contains(text(),"'+search_buyer+'")]/following-sibling:://span[@class="item-price"]')
for div in buyers:
print(";;;;;",div)
except Exception:
print("No buyer found")
getprice("Ben D. Rules")
(myvir) Administrators-Mac-mini:RESTAPI_ python JavaDeveloper$ python3 test.py
<Response [200]>
No buyer found
请您参考如下方法:
考虑使用 bs4 4.7.1 和 css 伪类 :contains。我发现 css 语法不那么脆弱。可能对 future 的读者有用。
import requests
from bs4 import BeautifulSoup as bs
def get_price(buyer_name, soup):
price = soup.select_one('div:contains("' + buyer_name + '") + .item-price')
if price is None:
price = 'Not found'
else:
price = price.text
return price
buyers = ['Patty Cakes', 'Derri Anne Connecticut', 'Moe Dess']
r = requests.get('http://econpy.pythonanywhere.com/ex/001.html')
soup = bs(r.content, 'html.parser')
for buyer_name in buyers:
print(get_price(buyer_name, soup))
更高效,传递买家名单:
def get_prices(buyers):
import requests
from bs4 import BeautifulSoup as bs
r = requests.get('http://econpy.pythonanywhere.com/ex/001.html')
soup = bs(r.content, 'html.parser')
results = [None] * len(buyers)
for index, buyer in enumerate(buyers):
price = soup.select_one('div:contains("' + buyer + '") + .item-price')
if price is None:
price = 'Not found'
else:
price = price.text
results[index] = price
return list(zip(buyers,results))
buyers = ['Patty Cakes', 'Derri Anne Connecticut', 'Moe Dess']
print(get_prices(buyers))
