Question

from requests import get
from bs4 import BeautifulSoup
from urllib.request import Request, urlopen

url = "http://www.metacritic.com/browse/games/score/metascore/year/pc/filtered?sort=desc&year_selected=2018"

尝试在页面上获取所有游戏名称，元数据和用户分数

这是我到目前为止所做的：

# not sure about this but it works (I was getting blocked by something and this the way I found around it)
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})

web_byte = urlopen(req).read()

webpage = web_byte.decode('utf-8')

#this grabs the all the text from the page
html_soup = BeautifulSoup(webpage, 'lxml')

game_containers = html_soup.find_all("div", class_="product_item product_title")

game_names = html_soup.find_all("div", class_="product_item product_title")
game_metascores_p = html_soup.find_all("div", class_="metascore_w small game positive")[0].text.strip()
game_metascores_m = html_soup.find_all("div", class_="metascore_w small game mixed")[0].text.strip()
game_user_s = html_soup.find_all("span", class_="data textscore textscore_favorable")[0].text.strip()

#lists to store the data
names = []
metascores = []
userscores = []

#Extract data from each game
for games in game_containers:

    name = games.find("div", class_="product_item product_title")
    print(name)

    metascore = games.find("div", class_="product_item product_title")[0].text.strip() or games.find_all("div", class_="metascore_w small game mixed")[0].text.strip()
    print(meta_score)

我知道此代码存在多个问题

是“name”和“metascore”不会返回我正在寻找的信息

也不确定如何结合game_metascores_p和game_metascores_m才能正常工作（我希望游戏名称与game_metascores_p和game_metascores_s相关联，如果有一个或另一个）

任何帮助将不胜感激

这就是游戏和metascore印刷的内容：

对于游戏然后是metascore（它重复100x）：

None
[]

我想要第一个（依此类推）：

In to the Breach
89

Answer 1

我明白了！

这段代码给了我想要的东西

# not sure about this but it works (I was getting blocked by something and this the way I found around it)
req = Request(url, headers={'User-Agent': 'Mozilla/5.0'})

web_byte = urlopen(req).read()

webpage = web_byte.decode('utf-8')

#this grabs the all the text from the page
html_soup = BeautifulSoup(webpage, 'html5lib')

#this is for selecting all the games in from 1 to 100 (the list of them)
game_containers = html_soup.find_all("div", class_="product_item product_title")

# print(game_containers)

game_names = html_soup.find_all("div", class_="product_item product_title")[0].text.strip()
game_metascores_p = html_soup.find_all("div", class_="metascore_w small game positive")[0].text.strip()
game_metascores_m = html_soup.find_all("div", class_="metascore_w small game mixed")[0].text.strip()
game_user_s = html_soup.find_all("span", class_="data textscore textscore_favorable")[0].text.strip()

# print(game_names)
# print(game_metascores_m or game_metascores_p)
# print(game_user_s)

#lists to store the data
names = []
metascores = []
userscores = []

#Extract data from each game
for games in game_containers:

#     game_names = html_soup.find_all("div", class_="product_item product_title")[0].text.strip()
#     game_metascores_p = html_soup.find_all("div", class_="metascore_w small game positive")[0].text.strip()
#     game_metascores_m = html_soup.find_all("div", class_="metascore_w small game mixed")[0].text.strip()
#     game_user_s = html_soup.find_all("span", class_="data textscore textscore_favorable")[0].text.strip()


    name = games.find()
    names.append(name.text.strip())


#     metascore = games.find("div", class_="product_item product_title") or games.find_all("div", class_="metascore_w small game mixed")
#     print(metascore)

# print(game_metascores_p)

没有给我metascore思想，我不知道为什么

Beautifulsoup试图提取所有游戏名称，元数据和用户分数

1 个答案: