本次爬虫学习使用了Selenium来模拟浏览器的行为,同时运用了PyQuery抓取相应信息,下面的代码只是简单地打印出来,而没有保存到本地。
import re
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from pyquery import PyQuery as pq
browser = webdriver.Chrome()
wait = WebDriverWait(browser, 10)
def search():
try:
browser.get('https://www.taobao.com')
input = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, "#q"))
)
submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "#J_TSearchForm > div.search-button > button"))) #参数为元组类型
input.send_keys('美食')
submit.click()
total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.total")))
get_products()
return total.text
except TimeoutException:
return search()
def next_page(page_number):
try:
input = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > input"))
)
submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit")))
input.clear()
input.send_keys(page_number)
submit.click()
wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > ul > li.item.active > span"), str(page_number)))
get_products()
except TimeoutException:
next_page(page_number)
def get_products():
wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .items .item')))
html = browser.page_source
doc = pq(html)
items = doc('#mainsrp-itemlist .items .item').items()
for item in items:
product = {
'image': item.find('.pic .img').attr('src'),
'price': item.find('.price').text(),
'deal': item.find('.deal-cnt').text()[:-3],
'title': item.find('.title').text(),
'shop': item.find('.shop').text(),
'location': item.find('.location').text()
}
print(product)
def main():
try:
total = search()
total = int(re.compile('(\d+)').search(total).group(1))
for i in range(2, total + 1):
next_page(i)
except Exception:
print('Error')
finally:
browser.close()
if __name__ == '__main__':
main()
当用Selenium模拟浏览器时,可能因为网速等原因,执行代码时,相应的内容还没有加载出来而出现问题,所以用到了WebDriverWait方法。等待的条件有很多,这里主要用到了三种EC.presence_of_element_located,EC.element_to_be_clickable和EC.text_to_be_present_in_element,输入的参数为一个元组。
在CSS中,井号(#)代表id,点号(.)代表class,大于号(>)代表选择直接子代。