我想從這個網站上抓取表格： https ://www.oddsportal.com/moving-margins/我需要表內的數據#moving_margins_content_overall我嘗試了這段代碼，但有些游戲包含許多 class="odd" 并且我不知道如何將 class="odd" 數據與 class="dark" 數據關聯import requestsfrom bs4 import BeautifulSoupimport timeimport jsonimport csvfrom selenium import webdriveru = 'https://www.oddsportal.com/moving-margins/'driver = webdriver.Chrome(executable_path=r"C:\chromedriver.exe")driver.get(u)driver.execute_script("window.scrollTo(0, document.body.scrollHeight)") driver.implicitly_wait(60) # secondstime.sleep(2)elem = driver.find_element_by_xpath("//*")source_code = elem.get_attribute("innerHTML")soup = BeautifulSoup(source_code, 'html.parser')for k in soup.select('#moving_margins_content_overall .table-main tbody tr'): sport = k.select_one('tr.dark th > a').get_text(strip=True) #sport country = soup.select_one('tr.dark th a:nth-child(3) span').get_text(strip=True) #country competition = soup.select_one('tr.dark th a:nth-child(5)').get_text(strip=True) #sport
1 回答
PIPIONE
TA貢獻1829條經驗 獲得超9個贊
您可以使用下面的代碼將所有數據存儲在一個列表中，其中頁面中的每一行都存儲為列表。
u = 'https://www.oddsportal.com/moving-margins/'
driver = webdriver.Chrome(executable_path=r"C:\chromedriver.exe")
driver.maximize_window()
driver.get(u)
#Use Explicit time wait for fast execution
WebDriverWait(driver, 30).until(EC.presence_of_element_located((By.CSS_SELECTOR, "#moving_margins_content_overall")))
driver.execute_script("window.scrollTo(0, document.body.scrollHeight)")
table_data = driver.find_elements_by_xpath("//div[@id='moving_margins_content_overall']//tr[@class='odd' or @class='dark']")
table =[]
# Creating a list of lists, where each list consist all data in each row either with class dark or odd
for data in table_data:
row = []
dark_row = data.find_elements_by_xpath((".//th//a"))
for col in dark_row:
row.append(col.text.replace("\n"," "))
row.append(data.find_element_by_xpath(".//following-sibling::tr//th[@class='first2']").text)# Add data in first2 th
odd_row = data.find_elements_by_xpath((".//following-sibling::tr[@class='odd']//td"))
for col in odd_row:
row.append(col.text.replace("\n", " "))
row.append(odd_row[-1].find_element_by_xpath('.//a').get_attribute("title")) #Add bookmaker name
table.append(row)
for t in table:
print(t)
輸出 正如您所看到的橄欖球聯盟比賽有兩種賠率，因此該比賽的列表很長。
添加回答
舉報
0/150
提交
取消