Question

在下面的代码中，我可以从＆＃34;进入Allowance＆＃34;中获取所有数据。在结果中，BlockFooter。在源中，大部分数据都在List（li）中，但是允许范围被span包围。我尝试了不同的变化但只是无法提取它。任何建议都值得赞赏。

     import csv
 from bs4 import BeautifulSoup
 import requests



 html = requests.get("http://www.sportinglife.com=156432).text

soup = BeautifulSoup(html,'lxml')

rows = []
for header in soup.find_all("div", class_="resultsBlockHeader"):
    track = header.find("div",        class_="track").get_text(strip=True).encode('ascii', 'ignore').strip("|")
    date = header.find("div",   class_="date").get_text(strip=True).encode('ascii', 'ignore').strip("|")
    datetime = header.find("div", class_="datetime").get_text(strip=True).encode('ascii', 'ignore').strip("|")
    grade = header.find("div", class_="grade").get_text(strip=True).encode('ascii', 'ignore').strip("|")
    distance = header.find("div", class_="distance").get_text(strip=True).encode('ascii', 'ignore').strip("|")
prizes = header.find("div", class_="prizes").get_text(strip=True).encode('ascii', 'ignore').strip("|")

results = header.find_next_sibling("div",  class_="resultsBlock").find_all("ul", class_="line1")
details = []
for result in results:
    fin = result.find("li", class_="fin").get_text(strip=True)
    greyhound = result.find("li", class_="greyhound").get_text(strip=True)
    trap = result.find("li", class_="trap").get_text(strip=True)
    sp = result.find("li", class_="sp").get_text(strip=True)
    timeSec = result.find("li", class_="timeSec").get_text(strip=True)
    timeDistance = result.find("li", class_="timeDistance").get_text(strip=True)

    details.append({"greyhound": greyhound, "sp": sp, "fin": fin, "timeSec": timeSec, "timeDistance": timeDistance, "trap": trap })


results = header.find_next_sibling("div",  class_="resultsBlock").find_all("ul", class_="line2")
for index, result in enumerate(results):
    trainer = result.find("li",  class_="trainer").get_text(strip=True)
    details[index]["trainer"] = trainer

results = header.find_next_sibling("div",  class_="resultsBlock").find_all("ul", class_="line3")
for index, result in enumerate(results):
    comment = result.find("li",  class_="comment").get_text(strip=True)
    details[index]["comment"] = comment

results = header.find_next_sibling("div",  class_="resultsBlock").find_all("ul", class_="line2")
for index, result in enumerate(results):
    firstessential = result.find("li",  class_="first essential").get_text(strip=True)
    details[index]["first essential"] = firstessential

results = header.find_next_sibling("div",  class_="resultsBlockFooter").find_all("ul", class_="line3")
for index, result in enumerate(results):
   goingAllowance = result.find("div",  class_="Going Allowance").get_text(strip=True)
   details[index]["Going Allowance"] = goingAllowance

for detail in details:
    detail.update({"track": track, "date": date, "datetime": datetime, "grade": grade, "prizes": prizes})
    rows.append(detail)
with open("abc.csv","a") as f:
    writer = csv.DictWriter(f,           [track","date","trap","fin","greyhound","datetime","sp","grade","distance","    prizes","timeSec","timeDistance","trainer","comment","first  essential","going Allowance"])

    for row in rows:
      writer.writerow(row)

Answer 1

为了将来参考而不是发布所有代码，只需包含相关部分即可。还包括您遇到问题的网站的html或部分。我查看了网站，我认为你的意思？

test = soup.find("div", {"class":"resultsBlockFooter"})
'<div class="resultsBlockFooter">
<div><span>Going Allowance:</span> -10</div>
<div><span>Forecast:</span> (3-4) £20.36 | <span>Tricast:</span> (3-4-2) £61.61</div>
</div>'

你想要<div><span>Going Allowance:</span> -10</div>？

allowance = test.content[1].text #.content can be a helpful list of the tags
"Going Allowance: -10"
forecast, tricast = test.content[3].text.split("|") #the rest of useful text

BS无法获取带有span标签的数据

1 个答案: