import requests
from bs4 import BeautifulSoup
url = "https://boulder.noshdelivery.co/restaurants"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
restaurant_wrapper = soup.find(class_ = "dd_rest_list")
restaurants = restaurant_wrapper.find_all(class_="menu__vendor-name")
restaurant_street_address = restaurant_wrapper.find("span", itemprop="streetAddress")
restaurant_address_locality = restaurant_wrapper.find("span", itemprop="addressLocality")
def extract_restaurant_data(restaurant):
restaurant_title = restaurant_wrapper.find(class_="menu__vendor-name")
return {
"title" : restaurant_title.text.strip(),
"streetAddress": restaurant_street_address.text.strip(),
"addressLocality": restaurant_address_locality.text.strip()
}
results = [extract_restaurant_data(restaurant) for restaurant in restaurants]
print(results)
我想知道為什么這段代碼會列印完全相同的資訊并且不會遍歷餐廳串列。
我的輸出是這個
{'title': '5280 Cafe At Rallysport', 'streetAddress': '2727 29th St.',
'addressLocality': 'Boulder'},
{'title': '5280 Cafe At Rallysport', 'streetAddress': '2727 29th St.', ' addressLocality': 'Boulder'}........
資訊是一樣的。我不知道為什么我的代碼不會遍歷“餐廳”串列中的不同名稱
uj5u.com熱心網友回復：
你只做了一個find資料。在每個部分上做一個find_all，然后zip把它們放在一起！
restaurant_details = zip(
restaurant_wrapper.find_all(class_="menu__vendor-name"),
restaurant_wrapper.find_all("span", itemprop="streetAddress"),
restaurant_wrapper.find_all("span", itemprop="addressLocality"),
)
results = [
{
"title": title.text.strip(),
"streetAddress": street_address.text.strip(),
"addressLocality": address_locality.text.strip()
}
for title, street_address, address_locality in restaurant_details
]
print(results)
uj5u.com熱心網友回復：
您的函式已restaurant_wrapper.find(class_="menu__vendor-name")寫入其中，因此每次運行時它只會列印 class 的第一次出現menu__vendor-name。
要在每次迭代中列印新餐廳的詳細資訊，您必須單獨訪問每個 Web 元素。
下面的代碼將允許您獲取所有餐廳的詳細資訊。
restwords = restaurant_wrapper.find_all("div", {"class": "dd_restwords"})
def extract_restaurant_data(restaurant):
title = restaurant.find("div", {"class": "menu__vendor-name"}).text
streetAddress = restaurant.find("span", {"itemprop": "streetAddress"}).text
addressLocality = restaurant.find("span", {"itemprop": "addressLocality"}).text
rest_data = {
"title": title,
"streetAddress": streetAddress,
"addressLocality": addressLocality
}
return rest_data
for restaurant in restwords:
print(extract_restaurant_data(restaurant))
轉載請註明出處，本文鏈接：https://www.uj5u.com/shujuku/456190.html