You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
|
|
|
|
import requests
|
|
|
|
|
import parsel
|
|
|
|
|
import csv
|
|
|
|
|
|
|
|
|
|
with open("data.csv", mode="a", encoding="utf-8", newline="") as f:
|
|
|
|
|
csv_writer = csv.DictWriter(f, fieldnames=["排名", "名字", "球队", "得分", "场次"])
|
|
|
|
|
if f.tell() == 0:
|
|
|
|
|
csv_writer.writeheader()
|
|
|
|
|
url = "https://nba.hupu.com/stats/players"
|
|
|
|
|
response = requests.get(url=url)
|
|
|
|
|
html_data = response.text
|
|
|
|
|
selector = parsel.Selector(html_data)
|
|
|
|
|
trs = selector.xpath('//tbody/tr[position()>1]')
|
|
|
|
|
for tr in trs:
|
|
|
|
|
ranking = tr.xpath("./td[1]/text()").get() # 获取排名
|
|
|
|
|
name = tr.xpath("./td[2]//a/text()").get() # 获取名字
|
|
|
|
|
team = tr.xpath("./td[3]//a/text()").get() # 获取球队
|
|
|
|
|
score = tr.xpath("./td[4]/text()").get() # 获取得分
|
|
|
|
|
venue = tr.xpath("./td[11]/text()").get() # 获取场次
|
|
|
|
|
print(f"排名: {ranking}, 名字: {name}, 球队: {team}, 得分: {score}, 场次: {venue}")
|
|
|
|
|
data_dict = {"排名": ranking,"名字": name,"球队": team,"得分": score,"场次": venue
|
|
|
|
|
}
|
|
|
|
|
csv_writer.writerow(data_dict)
|
