由于这个 URL 表是合并的,所以不能按预期打印出来,输出格式很奇怪,谢谢!
# -*- coding:UTF-8 -*-
from pyvirtualdisplay import Display
display = Display(visible=0, size=(1024, 768))
display.start()
from bs4 import BeautifulSoup
from selenium import webdriver
import re
driver = webdriver.Firefox()
driver.get("url")
soup = BeautifulSoup(driver.page_source.encode('utf-8'),'html.parser')
rows = soup.findAll("td", {"class" : re.compile('table_eng_small_text_.\d')})
result = ','.join(r.text for r in rows)
print(result)
driver.close()
display.stop()
预期输出:
1 10 SEASONS KING(T032) 12 7-1/4 7 4-3/4 1 1-1/4 1.09.35 25.06 22.31 21.98
2 2 HAPPY SOUND(V107) 1 1/2 1 3/4 2 1-1/4 1.09.56 23.90 22.71 22.95
3 14 NATURAL FRIENDSHIP(S359) 4 2-1/2 4 2-3/4 3 1-1/2 1.09.59 24.30 22.75 22.54
4 13 LUCKY PLACE(T004) 14 10 13 6-1/2 4 3 1.09.84 25.50 22.15 22.19
5 9 NO LAUGHING MATTER(V032) 9 5-3/4 9 5 5 3-1/2 1.09.89 24.82 22.59 22.48
6 1 FREE NOVEMBER(T123) 5 4 5 3-3/4 6 4-1/2 1.10.07 24.54 22.67 22.86
7 7 FRIENDS FOREVER(T079) 2 1/2 2 3/4 7 4-1/2 1.10.08 23.98 22.75 23.35
8 5 REAL SUPREME(L247) 3 1-1/2 3 2-1/4 8 5-3/4 1.10.27 24.14 22.83 23.30
9 6 BE THERE AHEAD(S193) 6 4-1/4 6 3-3/4 9 6-1/4 1.10.34 24.58 22.63 23.13
10 8 GOLD PRECIOUS(P364) 13 8-1/4 11 6-1/2 10 6-3/4 1.10.41 25.22 22.43 22.76
11 11 DUTCH WINDMILL(T288) 10 5-3/4 14 7 11 7 1.10.48 24.82 22.91 22.75
12 3 HAPPY THREE(V162) 11 5-3/4 8 4-3/4 12 7 1.10.49 24.82 22.55 23.12
13 4 SILVER GATSBY(T161) 8 5-1/2 12 6-1/2 13 7-1/2 1.10.56 24.78 22.87 22.91
14 12 CHANS DELIGHT(P420) 7 4-1/2 10 5-3/4 14 9-3/4 1.10.92 24.62 22.91 23.39