Question

我正在使用selenium迭代变量参数的不同组合并从网站下载数据。但是，当没有数据时，for循环功能停止工作;我还注意到，当硒停止时，网页包含标记为“无法生成结果”的文本。因此，我想使用带有selenium的if语句来搜索“无法生成结果”，如果找到上述文本则跳到下一个循环。一个例子是这样的：

import os
from selenium import webdriver
import zipfile
import pandas as pd
import time

for i in to_loop:
    # directories
    link = 'http://www.gaez.iiasa.ac.at/w/ctrl?
_flow=Vwr&_view=Welcome&idAS=0&idFS=0&fieldmain=main_&idPS=0'

    ## Access Chrome Driver to use selenium
    # Define Download Directory
    chrome_options = webdriver.ChromeOptions()
    prefs = {'download.default_directory': 'C:/.../Download'}
    chrome_options.add_experimental_option('prefs', prefs)
    driver = webdriver.Chrome(
        executable_path='C:/.../chromedriver.exe',
        chrome_options=chrome_options)
    driver.get(link)

    # Enter username and password
    driver.find_element_by_name('_username').send_keys(username)
    driver.find_element_by_name('_password').send_keys(password)
    driver.find_element_by_id('buttonSubmit__login').click()

    # Click on Suitability and Potential Yield link
    driver.find_element_by_name('_targetfieldmain=main_py&_...').click()

    # Click on Agro-ecological suitability and productivity link
    driver.find_element_by_name('&fieldmain=main_py&idPS=0&...').click()
    # Click on Agro-ecological suitability and productivity list
    driver.find_element_by_css_selector('input[value="
{}"]'.format(i[0])).click()
    # Click on crop link
    driver.find_element_by_css_selector("input.linksubmit[value=\"▸ 
Crop\"]").click()
    AES_and_P = i[0]

    driver.find_element_by_css_selector('input[value="
{}"]'.format(i[1])).click()
    # Click on Water Supply Link
    driver.find_element_by_css_selector("input.linksubmit[value=\"▸ Water 
Supply\"]").click()
    Crop = i[1]

    driver.find_element_by_css_selector('input[value="
{}"]'.format(i[2])).click()
    # Click on Input Level Link
    driver.find_element_by_css_selector("input.linksubmit[value=\"▸ Input 
Level\"]").click()
    Water_Supply = i[2]

    driver.find_element_by_css_selector('input[value="
{}"]'.format(i[3])).click()
    Input_Level = i[3]

    # If statement to skip to next loop if text found
    data_check = driver.find_elements_by_partial_link_text('Cannot produce 
results.')
    if data_check[0].is_displayed():
        continue

    # Click on Time Period and Select Baseline
    driver.find_element_by_css_selector("input.linksubmit[value=\"▸ Time 
Period\"]").click()
    driver.find_element_by_css_selector("input.linksubmit[value=\"1961-
1990\"]").click()
    # Click on Geographic Areas Link
    driver.find_element_by_css_selector("input.linksubmit[value=\"▸ 
Geographic Areas\"]").click()
    # Unselect all countries
    driver.find_element_by_xpath('//*[@id="fieldareaList__pln-1"]').click()
    # Close tab for Northern Africa
    driver.find_element_by_xpath('//*[@id="rg1-66-Northern 
Africa"]/span').click()
    # Wait 1 second
    time.sleep(1)
    # Click geographic area then country
    driver.find_element_by_xpath('//label[text()="{}"]/following-
sibling::span'.format(geographic_area)).click()
    driver.find_element_by_xpath('//label[text()="
{}"]'.format(country)).click()
    # Click on Map Link
    driver.find_element_by_css_selector("input.linksubmit[value=\"▸ 
Map\"]").click()
    # Download Data
    driver.find_element_by_xpath('//*[@id="buttons"]/a[4]/img').click()

    # Wait 2 seconds
    time.sleep(2)

    # Download blah blah
    path = 'C:/.../Download'
    destination_folder = 'C:/.../CSV_Files'
    file_list = [os.path.join(path, f) for f in os.listdir(path)]
    time_sorted_list = sorted(file_list, key=os.path.getmtime)
    file_name = time_sorted_list[-1]
    # decompress the zipped file here
    myzip = zipfile.ZipFile(file_name)

    # Wait 1 second
    time.sleep(1)

    myzip.extract('data.asc', destination_folder)

    # Save data.asc file as .csv and rename reflects download selections
    newfilename = country + Crop + Water_Supply + Input_Level + AES_and_P
    df = pd.read_table(os.path.join(destination_folder, 'data.asc'), 
sep="\s+", skiprows=6, header=None)
    df.to_csv(os.path.join(destination_folder, '{}.csv'.format(newfilename)))

    # Delete downloaded data.asc file
    delete_data_file = "C:/.../CSV_Files/data.asc"
    # if file exists, delete it
    if os.path.isfile(delete_data_file):
        os.remove(delete_data_file)
    else:  # Show error
        print("Error: %s file not found" % delete_data_file)

    driver.close()

但是，此代码只是在继续时停止函数，不完成代码的下载部分，并遍历循环的其余部分。有任何想法如何解决这个问题？另外，如果问题令人困惑，请告诉我。

Answer 1

在我们在评论中讨论之后，我相信我至少看到了你的部分问题。 python continue keyword并不代表＆＃34;继续其余的控制流程＆＃34;它意味着＆＃34;继续循环的下一次迭代，跳过＆＃34;。

之后的所有内容

例如，在下面的python代码中：

a = []
for i in range(10):
    if i == 5:
        continue
    a.append(i)

print(a)

结果将是：

[0, 1, 2, 3, 4, 6, 7, 8, 9]

而不是，使用您之前的逻辑

[5]

因此，要在continue上修复代码，您需要翻转逻辑，以便在条件不为真时跳过，例如：

 if not data_check[0].is_displayed():
     continue

虽然我个人从来没有遇到过和你一样犯过同样错误的人，但我从语义上强调，似乎更有意义的是，＃34;继续＆＃34;将继续讨论该计划的下一部分。 continue中的蟒蛇选择在很大程度上取决于continue作为关键字particularly in C的历史用法。在这种情况下，我们可以将continue更多地视为break语句的扩展名为＆＃34; skip＆＃34;。

Python - For循环if语句跳到Selenium中的下一次迭代

1 个答案: