图片.png
参考答案
#!/usr/bin/python3# -*- coding: utf-8 -*-# 讨论钉钉免费群21745728 qq群144081101 567351477# CreateDate: 2018-10-20
from selenium import webdriver
driver = webdriver.Firefox()
driver.implicitly_wait(30)
driver.get('http://example.webscraping.com/places/default/search')
driver.find_element_by_id('search_term').send_keys('.')
js = "document.getElementById('page_size').options[1].text = '300';"driver.execute_script(js)
driver.find_element_by_id('search').click()
links = driver.find_elements_by_css_selector('#results a')
countries = [link.text for link in links]
print(len(countries))
print(countries)
driver.close()本例参考书籍：用Python写网络爬虫.pdf
selenium 上机实操: 下拉刷新框中所有内容(javascript实现)打开：http://www.webscrapingfordatascience.com/complexjavascript/
抓取框中所有内容。该框按住鼠标中键下滚，会有刷新内容，直至完全加载
图片.png
参考答案
#!/usr/bin/python3# -*- coding: utf-8 -*-# 讨论钉钉免费群21745728 qq群144081101 567351477# CreateDate: 2018-10-18from selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.common.exceptions import TimeoutExceptionclass at_least_n_elements_found(object):
def __init__(self, locator, n):
self.locator = locator
self.n = n def __call__(self, driver):
elements = driver.find_elements(*self.locator) if len(elements) >= self.n: return elements else: return False
url = 'http://www.webscrapingfordatascience.com/complexjavascript/'driver = webdriver.Chrome()
driver.get(url)# Use an implicit wait for cases where we don't use an explicit onedriver.implicitly_wait(10)
div_element = driver.find_element_by_class_name('infinite-scroll')
quotes_locator = (By.CSS_SELECTOR, ".quote:not(.decode)")
nr_quotes = 0while True: # Scroll down to the bottom
driver.execute_script('arguments[0].scrollTop = arguments[0].scrollHeight',
div_element)
# Try to fetch at least nr_quotes+1 quotes
try:
all_quotes = WebDriverWait(driver, 3).until(
at_least_n_elements_found(quotes_locator, nr_quotes + 1)) except TimeoutException as ex: # No new quotes found within 3 seconds, assume this is all there is
print("... done!") break
# Otherwise, update the quote counter
nr_quotes = len(all_quotes)
print("... now seeing", nr_quotes, "quotes")
# all_quotes will contain all the quote elementsprint(len(all_quotes), 'quotes foundn')for quote in all_quotes:
print(quote.text)
input('Press ENTER to close the automated browser')
driver.quit()
作者：python作业AI毕业设计
链接：https://www.jianshu.com/p/62afcd9ec11d
