Python 脚本突然停止爬行,没有错误或异常
我不知道为什么,但我的脚本一旦点击就会停止爬行。没有错误、异常或警告,所以我有点不知所措 有人能帮我吗 附言 打印Python 脚本突然停止爬行,没有错误或异常,python,selenium,python-requests,geckodriver,urllib3,Python,Selenium,Python Requests,Geckodriver,Urllib3,我不知道为什么,但我的脚本一旦点击就会停止爬行。没有错误、异常或警告,所以我有点不知所措 有人能帮我吗 附言 打印项的长度也会引发一些奇怪的行为。它不总是返回32(与每页上的项目数相对应),而是打印第一页的32,第二页的64,第三页的96,依此类推。我通过使用//div[contains(@id,“100\u dealView”)]/div[contains(@class,“dealContainer”)]而不是//div[contains(@id,“100\u dealView”)]作为项变量
项的长度
也会引发一些奇怪的行为。它不总是返回32(与每页上的项目数相对应),而是打印第一页的32
,第二页的64
,第三页的96
,依此类推。我通过使用//div[contains(@id,“100\u dealView”)]/div[contains(@class,“dealContainer”)]
而不是//div[contains(@id,“100\u dealView”)]
作为项
变量的XPath解决了这个问题。我希望这就是它在第9页出现问题的原因。我现在正在做测试更新:现在正在抓取第10页及以后的内容,因此问题已得到解决。根据您的问题,错误消息
HTTPConnectionPool(host='127.0.0.1', port=58992): Max retries exceeded with url: /session/e8beed9b-4faa-4e91-a659-56761cb604d7/element (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x0000022D31378A58>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))
* Fix ability to set timeout for urllib3 (#6286)
合并是:
结论
升级到Selenium 3.14.1后,您将能够设置超时并查看规范回溯,并能够采取所需的操作
工具书类
一些相关参考资料:
这个用例 我已经从你的网站上下载了你的完整脚本。我不得不对您现有的代码进行一些调整,如下所示:
- 正如您所使用的:
ua_string = random.choice(ua_strings)
random
作为:
import random
- 您已经创建了变量“下一步”按钮,但尚未使用它。我总结了以下四行:
作为:next_button = WebDriverWait(ff, 15).until( EC.text_to_be_present_in_element((By.PARTIAL_LINK_TEXT, 'Next→'), 'Next→') ) ff.find_element(By.PARTIAL_LINK_TEXT, 'Next→').click()
- 您修改的代码块将是:
# -*- coding: utf-8 -*- from selenium import webdriver from selenium.webdriver.firefox.options import Options from selenium.webdriver.common.by import By from selenium.webdriver.support import expected_conditions as EC from selenium.webdriver.support.ui import WebDriverWait import time import random """ Set Global Variables """ ua_strings = ['Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'] already_scraped_product_titles = [] """ Create Instances of WebDriver """ def create_webdriver_instance(): ua_string = random.choice(ua_strings) profile = webdriver.FirefoxProfile() profile.set_preference('general.useragent.override', ua_string) options = Options() options.add_argument('--headless') return webdriver.Firefox(profile) """ Construct List of UA Strings """ def fetch_ua_strings(): ff = create_webdriver_instance() ff.get('https://techblog.willshouse.com/2012/01/03/most-common-user-agents/') ua_strings_ff_eles = ff.find_elements_by_xpath('//td[@class="useragent"]') for ua_string in ua_strings_ff_eles: if 'mobile' not in ua_string.text and 'Trident' not in ua_string.text: ua_strings.append(ua_string.text) ff.quit() """ Log in to Amazon to Use SiteStripe in order to Generate Affiliate Links """ def log_in(ff): ff.find_element(By.XPATH, '//a[@id="nav-link-yourAccount"] | //a[@id="nav-link-accountList"]').click() ff.find_element(By.ID, 'ap_email').send_keys('anthony_falez@hotmail.com') ff.find_element(By.ID, 'continue').click() ff.find_element(By.ID, 'ap_password').send_keys('lo0kyLoOkYig0t4h') ff.find_element(By.NAME, 'rememberMe').click() ff.find_element(By.ID, 'signInSubmit').click() """ Build Lists of Product Page URLs """ def initiate_crawl(): def refresh_page(url): ff = create_webdriver_instance() ff.get(url) ff.find_element(By.XPATH, '//*[@id="FilterItemView_sortOrder_dropdown"]/div/span[2]/span/span/span/span').click() ff.find_element(By.XPATH, '//a[contains(text(), "Discount - High to Low")]').click() items = WebDriverWait(ff, 15).until( EC.visibility_of_all_elements_located((By.XPATH, '//div[contains(@id, "100_dealView_")]')) ) for count, item in enumerate(items): slashed_price = item.find_elements(By.XPATH, './/span[contains(@class, "a-text-strike")]') active_deals = item.find_elements(By.XPATH, './/*[contains(text(), "Add to Cart")]') # For Groups of Items on Sale # active_deals = //*[contains(text(), "Add to Cart") or contains(text(), "View Deal")] if len(slashed_price) > 0 and len(active_deals) > 0: product_title = item.find_element(By.ID, 'dealTitle').text if product_title not in already_scraped_product_titles: already_scraped_product_titles.append(product_title) url = ff.current_url # Scrape Details of Each Deal #extract(ff, item.find_element(By.ID, 'dealImage').get_attribute('href')) print(product_title[:10]) ff.quit() refresh_page(url) break if count+1 is len(items): try: print('') print('new page') WebDriverWait(ff, 15).until(EC.text_to_be_present_in_element((By.PARTIAL_LINK_TEXT, 'Next→'), 'Next→')) ff.find_element(By.PARTIAL_LINK_TEXT, 'Next→').click() time.sleep(10) url = ff.current_url print(url) print('') ff.quit() refresh_page(url) except Exception as error: """ ff.find_element(By.XPATH, '//*[@id="pagination-both-004143081429407891"]/ul/li[9]/a').click() url = ff.current_url ff.quit() refresh_page(url) """ print('cannot find ff.find_element(By.PARTIAL_LINK_TEXT, "Next?")') print('Because of... {}'.format(error)) ff.quit() refresh_page('https://www.amazon.ca/gp/goldbox/ref=gbps_ftr_s-3_4bc8_dct_10-?gb_f_c2xvdC0z=sortOrder:BY_SCORE,discountRanges:10-25%252C25-50%252C50-70%252C70-&pf_rd_p=f5836aee-0969-4c39-9720-4f0cacf64bc8&pf_rd_s=slot-3&pf_rd_t=701&pf_rd_i=gb_main&pf_rd_m=A3DWYIK6Y9EEQB&pf_rd_r=CQ7KBNXT36G95190QJB1&ie=UTF8') #def extract_info(ff, url): fetch_ua_strings() initiate_crawl()
- 控制台输出:使用Selenium v3.14.0和Firefox Quantum v62.0.3,我可以在控制台上提取以下输出:
J.Rosée Si B.Catcher Bluetooth4 FRAM G4164 Major Crim 20% off Oh True Blood Prime-Line Marathon 3 True Blood B.Catcher 4 Film Fav True Blood Texture Pa Westinghou True Blood ThermoPro ... ... ...
我稍微调整了代码,它似乎起作用了。变化:
import random
语句,因为它已被使用,没有它将无法运行
在product\u title
循环中,这些行被删除:
ff.quit()
,刷新页面(url)
和break
ff.quit()
语句将导致致命(连接)错误,导致脚本中断
如果计数+1==len(项目):
你监控了爬行过程吗?第9页还有像“更多”这样的按钮吗?@jihan1008一切都被监控着。我检查了xpath,所有内容,似乎没有任何内容被破坏。您可以使用不同的浏览器版本进行检查。我无法让您的脚本运行,但似乎在某个点上,您会得到长度为0的项,因此枚举循环不会发生。尝试在循环之前打印项目的长度,看看代码结束之前会发生什么。@AndrewMcDowell好主意!我在pt,我相信它一定在剧本的其他地方。我目前已经设置了一组
time.sleep(n)
s,并用它运行了一个测试。之后我会打印长度!感谢您的输入,我的问题中的HTTPConnectionPool
错误是一个异常值。脚本工作得非常好,直到它在第9页突然停止,没有错误或异常。我设置但未使用“下一步”按钮的唯一原因是,我试图对此进行故障排除,认为可能与此有关,但从未重置它。这里的问题是,为什么它在完成第9页后会停止爬行/刮取?哦,也许这就是为什么我从未重置它<代码>WebDriverWait(ff,15)。直到(EC.text)在元素中出现((By.PARTIAL\u LINK\u text,'下一步→'), '下一个→')).单击()返回一个不可单击的布尔对象。您的code@Anthony根据你的观察,我对我的解决方案做了一些小的修改。我本可以优化你的代码,并执行相同的web废弃操作,只打开一次Firefox浏览器客户端并遍历各种产品。但是请注意您的逻辑和创新我建议您通过所需的最小更改。请您尝试更新的解决方案并告诉我状态好吗?事实上,几天前我自己解决了这个问题。为了清晰起见,我已经更新了我的问题,并再次更新了它。是的,我不知道有什么具体原因使用单个实例遍历网站,而不是创建多个实例。尽管现在我考虑到了这一点,使用ff.back()创建新实例甚至可能不是必需的
功能,但它肯定更直截了当。我有空的时候会给你的答案看一看!谢谢你尝试解决我的问题
WebDriverWait(ff, 15).until(EC.text_to_be_present_in_element((By.PARTIAL_LINK_TEXT, 'Next→'), 'Next→'))
ff.find_element(By.PARTIAL_LINK_TEXT, 'Next→').click()
# -*- coding: utf-8 -*-
from selenium import webdriver
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
import time
import random
""" Set Global Variables
"""
ua_strings = ['Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36']
already_scraped_product_titles = []
""" Create Instances of WebDriver
"""
def create_webdriver_instance():
ua_string = random.choice(ua_strings)
profile = webdriver.FirefoxProfile()
profile.set_preference('general.useragent.override', ua_string)
options = Options()
options.add_argument('--headless')
return webdriver.Firefox(profile)
""" Construct List of UA Strings
"""
def fetch_ua_strings():
ff = create_webdriver_instance()
ff.get('https://techblog.willshouse.com/2012/01/03/most-common-user-agents/')
ua_strings_ff_eles = ff.find_elements_by_xpath('//td[@class="useragent"]')
for ua_string in ua_strings_ff_eles:
if 'mobile' not in ua_string.text and 'Trident' not in ua_string.text:
ua_strings.append(ua_string.text)
ff.quit()
""" Log in to Amazon to Use SiteStripe in order to Generate Affiliate Links
"""
def log_in(ff):
ff.find_element(By.XPATH, '//a[@id="nav-link-yourAccount"] | //a[@id="nav-link-accountList"]').click()
ff.find_element(By.ID, 'ap_email').send_keys('anthony_falez@hotmail.com')
ff.find_element(By.ID, 'continue').click()
ff.find_element(By.ID, 'ap_password').send_keys('lo0kyLoOkYig0t4h')
ff.find_element(By.NAME, 'rememberMe').click()
ff.find_element(By.ID, 'signInSubmit').click()
""" Build Lists of Product Page URLs
"""
def initiate_crawl():
def refresh_page(url):
ff = create_webdriver_instance()
ff.get(url)
ff.find_element(By.XPATH, '//*[@id="FilterItemView_sortOrder_dropdown"]/div/span[2]/span/span/span/span').click()
ff.find_element(By.XPATH, '//a[contains(text(), "Discount - High to Low")]').click()
items = WebDriverWait(ff, 15).until(
EC.visibility_of_all_elements_located((By.XPATH, '//div[contains(@id, "100_dealView_")]'))
)
for count, item in enumerate(items):
slashed_price = item.find_elements(By.XPATH, './/span[contains(@class, "a-text-strike")]')
active_deals = item.find_elements(By.XPATH, './/*[contains(text(), "Add to Cart")]')
# For Groups of Items on Sale
# active_deals = //*[contains(text(), "Add to Cart") or contains(text(), "View Deal")]
if len(slashed_price) > 0 and len(active_deals) > 0:
product_title = item.find_element(By.ID, 'dealTitle').text
if product_title not in already_scraped_product_titles:
already_scraped_product_titles.append(product_title)
url = ff.current_url
# Scrape Details of Each Deal
#extract(ff, item.find_element(By.ID, 'dealImage').get_attribute('href'))
print(product_title[:10])
ff.quit()
refresh_page(url)
break
if count+1 is len(items):
try:
print('')
print('new page')
WebDriverWait(ff, 15).until(EC.text_to_be_present_in_element((By.PARTIAL_LINK_TEXT, 'Next→'), 'Next→'))
ff.find_element(By.PARTIAL_LINK_TEXT, 'Next→').click()
time.sleep(10)
url = ff.current_url
print(url)
print('')
ff.quit()
refresh_page(url)
except Exception as error:
"""
ff.find_element(By.XPATH, '//*[@id="pagination-both-004143081429407891"]/ul/li[9]/a').click()
url = ff.current_url
ff.quit()
refresh_page(url)
"""
print('cannot find ff.find_element(By.PARTIAL_LINK_TEXT, "Next?")')
print('Because of... {}'.format(error))
ff.quit()
refresh_page('https://www.amazon.ca/gp/goldbox/ref=gbps_ftr_s-3_4bc8_dct_10-?gb_f_c2xvdC0z=sortOrder:BY_SCORE,discountRanges:10-25%252C25-50%252C50-70%252C70-&pf_rd_p=f5836aee-0969-4c39-9720-4f0cacf64bc8&pf_rd_s=slot-3&pf_rd_t=701&pf_rd_i=gb_main&pf_rd_m=A3DWYIK6Y9EEQB&pf_rd_r=CQ7KBNXT36G95190QJB1&ie=UTF8')
#def extract_info(ff, url):
fetch_ua_strings()
initiate_crawl()
J.Rosée Si
B.Catcher
Bluetooth4
FRAM G4164
Major Crim
20% off Oh
True Blood
Prime-Line
Marathon 3
True Blood
B.Catcher
4 Film Fav
True Blood
Texture Pa
Westinghou
True Blood
ThermoPro
...
...
...
# -*- coding: utf-8 -*-
from selenium import webdriver
from selenium.webdriver import Firefox
from selenium.webdriver.firefox.options import Options
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.ui import WebDriverWait
import time
import random
""" Set Global Variables
"""
ua_strings = ['Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36']
already_scraped_product_titles = []
""" Create Instances of WebDriver
"""
def create_webdriver_instance():
ua_string = random.choice(ua_strings)
profile = webdriver.FirefoxProfile()
profile.set_preference('general.useragent.override', ua_string)
options = Options()
options.add_argument('--headless')
return webdriver.Firefox(profile)
""" Construct List of UA Strings
"""
def fetch_ua_strings():
ff = create_webdriver_instance()
ff.get('https://techblog.willshouse.com/2012/01/03/most-common-user-agents/')
ua_strings_ff_eles = ff.find_elements_by_xpath('//td[@class="useragent"]')
for ua_string in ua_strings_ff_eles:
if 'mobile' not in ua_string.text and 'Trident' not in ua_string.text:
ua_strings.append(ua_string.text)
ff.quit()
""" Build Lists of Product Page URLs
"""
def initiate_crawl():
def refresh_page(url):
ff = create_webdriver_instance()
ff.get(url)
ff.find_element(By.XPATH, '//*[@id="FilterItemView_sortOrder_dropdown"]/div/span[2]/span/span/span/span').click()
ff.find_element(By.XPATH, '//a[contains(text(), "Discount - High to Low")]').click()
items = WebDriverWait(ff, 15).until(
EC.visibility_of_all_elements_located((By.XPATH, '//div[contains(@id, "100_dealView_")]'))
)
print(items)
for count, item in enumerate(items):
slashed_price = item.find_elements(By.XPATH, './/span[contains(@class, "a-text-strike")]')
active_deals = item.find_elements(By.XPATH, './/*[contains(text(), "Add to Cart")]')
# For Groups of Items on Sale
# active_deals = //*[contains(text(), "Add to Cart") or contains(text(), "View Deal")]
if len(slashed_price) > 0 and len(active_deals) > 0:
product_title = item.find_element(By.ID, 'dealTitle').text
if product_title not in already_scraped_product_titles:
already_scraped_product_titles.append(product_title)
url = ff.current_url
# Scrape Details of Each Deal
#extract(ff, item.find_element(By.ID, 'dealImage').get_attribute('href'))
print(product_title[:10])
# This ff.quit()-line breaks connection which breaks things.:
#ff.quit()
# And why
#refresh_page(url)
#break
# 'is' tests for object equality; == tests for value equality:
if count+1 == len(items):
try:
print('')
print('new page')
next_button = WebDriverWait(ff, 15).until(
EC.text_to_be_present_in_element((By.PARTIAL_LINK_TEXT, 'Next→'), 'Next→')
)
ff.find_element(By.PARTIAL_LINK_TEXT, 'Next→').click()
time.sleep(3)
url = ff.current_url
print(url)
print('')
ff.quit()
refresh_page(url)
except Exception as error:
"""
ff.find_element(By.XPATH, '//*[@id="pagination-both-004143081429407891"]/ul/li[9]/a').click()
url = ff.current_url
ff.quit()
refresh_page(url)
"""
print('cannot find ff.find_element(By.PARTIAL_LINK_TEXT, "Next→")')
print('Because of... {}'.format(error))
ff.quit()
refresh_page('https://www.amazon.ca/gp/goldbox/ref=gbps_ftr_s-3_4bc8_dct_10-?gb_f_c2xvdC0z=sortOrder:BY_SCORE,discountRanges:10-25%252C25-50%252C50-70%252C70-&pf_rd_p=f5836aee-0969-4c39-9720-4f0cacf64bc8&pf_rd_s=slot-3&pf_rd_t=701&pf_rd_i=gb_main&pf_rd_m=A3DWYIK6Y9EEQB&pf_rd_r=CQ7KBNXT36G95190QJB1&ie=UTF8')
#def extract_info(ff, url):
fetch_ua_strings()
initiate_crawl()