今日内容:
一 Selenium剩余部分
二 BeautifulSoup4
一 Selenium剩余部分
1.元素交互操作:
- 点击、清除
click
clear
- ActionChains
是一个动作链对象，需要把driver驱动传给它。
动作链对象可以操作一系列设定好的动作行为。
- iframe的切换
driver.switch_to.frame('iframeResult')
- 执行js代码
execute_script()
爬取京东商品信息
# 初级版:
# from tank!
# '''
# import time
# from selenium import webdriver
# from selenium.webdriver.common.keys import Keys
#
# driver = webdriver.Chrome()
#
# num = 1
#
# try:
# driver.implicitly_wait(10)
# # 往京东发送请求
# driver.get('https://www.jd.com/')
#
# # 往京东主页输入框输入墨菲定律，按回车键
# input_tag = driver.find_element_by_id('key')
# input_tag.send_keys('墨菲定律')
# input_tag.send_keys(Keys.ENTER)
#
# time.sleep(5)
#
#
# good_list = driver.find_elements_by_class_name('gl-item')
# for good in good_list:
# # print(good)
# # 商品名称
# good_name = good.find_element_by_css_selector('.p-name em').text
# # print(good_name)
#
# # 商品链接
# good_url = good.find_element_by_css_selector('.p-name a').get_attribute('href')
# # print(good_url)
#
# # 商品价格
# good_price = good.find_element_by_class_name('p-price').text
# # print(good_price)
#
# # 商品评价
# good_commit = good.find_element_by_class_name('p-commit').text
#
# good_content = f'''
# num: {num}
# 商品名称: {good_name}
# 商品链接: {good_url}
# 商品价格: {good_price}
# 商品评价: {good_commit}
# \n
# '''
#
# print(good_content)
#
# with open('jd.txt', 'a', encoding='utf-8') as f:
# f.write(good_content)
# num += 1
#
# print('商品信息写入成功!')
#
#
# finally:
# driver.close()
'''
中级版
'''
# import time
# from selenium import webdriver
# from selenium.webdriver.common.keys import Keys
#
# driver = webdriver.Chrome()
#
# num = 1
#
# try:
# driver.implicitly_wait(10)
# # 往京东发送请求
# driver.get('https://www.jd.com/')
#
# # 往京东主页输入框输入墨菲定律，按回车键
# input_tag = driver.find_element_by_id('key')
# input_tag.send_keys('墨菲定律')
# input_tag.send_keys(Keys.ENTER)
#
# time.sleep(5)
#
# # 下拉滑动5000px
# js_code = '''
# window.scrollTo(0, 5000)
# '''
#
# driver.execute_script(js_code)
#
# # 等待5秒，待商品数据加载
# time.sleep(5)
#
# good_list = driver.find_elements_by_class_name('gl-item')
# for good in good_list:
# # print(good)
# # 商品名称
# good_name = good.find_element_by_css_selector('.p-name em').text
# # print(good_name)
#
# # 商品链接
# good_url = good.find_element_by_css_selector('.p-name a').get_attribute('href')
# # print(good_url)
#
# # 商品价格
# good_price = good.find_element_by_class_name('p-price').text
# # print(good_price)
#
# # 商品评价
# good_commit = good.find_element_by_class_name('p-commit').text
#
# good_content = f'''
# num: {num}
# 商品名称: {good_name}
# 商品链接: {good_url}
# 商品价格: {good_price}
# 商品评价: {good_commit}
# \n
# '''
#
# print(good_content)
#
# with open('jd.txt', 'a', encoding='utf-8') as f:
# f.write(good_content)
# num += 1
#
# print('商品信息写入成功!')
#
# # 找到下一页并点击
# next_tag = driver.find_element_by_class_name('pn-next')
# next_tag.click()
#
# time.sleep(10)
#
# finally:
# driver.close()
'''
狂暴版
'''
import time
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
def get_good(driver):
num = 1
try:
time.sleep(5)
# 下拉滑动5000px
js_code = '''
window.scrollTo(0, 5000)
'''
driver.execute_script(js_code)
# 等待5秒，待商品数据加载
time.sleep(5)
good_list = driver.find_elements_by_class_name('gl-item')
for good in good_list:
# 商品名称
good_name = good.find_element_by_css_selector('.p-name em').text
# 商品链接
good_url = good.find_element_by_css_selector('.p-name a').get_attribute('href')
# 商品价格
good_price = good.find_element_by_class_name('p-price').text
# 商品评价
good_commit = good.find_element_by_class_name('p-commit').text
good_content = f'''
num: {num}
商品名称: {good_name}
商品链接: {good_url}
商品价格: {good_price}
商品评价: {good_commit}
\n
'''
print(good_content)
with open('jd.txt', 'a', encoding='utf-8') as f:
f.write(good_content)
num += 1
print('商品信息写入成功!')
# 找到下一页并点击
next_tag = driver.find_element_by_class_name('pn-next')
next_tag.click()
time.sleep(5)
# 递归调用函数本身
get_good(driver)
finally:
driver.close()
if __name__ == '__main__':
driver = webdriver.Chrome()
try:
driver.implicitly_wait(10)
# 往京东发送请求
driver.get('https://www.jd.com/')
# 往京东主页输入框输入墨菲定律，按回车键
input_tag = driver.find_element_by_id('key')
input_tag.send_keys('墨菲定律')
input_tag.send_keys(Keys.ENTER)
# 调用获取商品信息函数
get_good(driver)
finally:
driver.close()
bs4搜索文档树
find: 找第一个
find_all: 找所有
标签查找与属性查找:
name 属性匹配
name 标签名
attrs 属性查找匹配
text 文本匹配
标签:
- 字符串过滤器
字符串全局匹配
- 正则过滤器
re模块匹配
- 列表过滤器
列表内的数据匹配
- bool过滤器
True匹配
- 方法过滤器
用于一些要的属性以及不需要的属性查找。
属性:
- class_
- id
'''
html_doc = """The Dormouse's story $37
Once upon a time there were three little sisters; and their names wereElsieLacie andTillieand they lived at the bottom of a well.
...
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc, 'lxml')
# name 标签名
# attrs 属性查找匹配
# text 文本匹配
# find与find_all搜索文档
'''
字符串过滤器
'''
p = soup.find(name='p')
p_s = soup.find_all(name='p')
print(p)
print(p_s)
# name + attrs
p = soup.find(name='p', attrs={"id": "p"})
print(p)
# name + text
tag = soup.find(name='title', text="The Dormouse's story")
print(tag)
# name + attrs + text
tag = soup.find(name='a', attrs={"class": "sister"}, text="Elsie")
print(tag)
'''
- 正则过滤器
re模块匹配
'''
import re
# name
# 根据re模块匹配带有a的节点
a = soup.find(name=re.compile('a'))
print(a)
a_s = soup.find_all(name=re.compile('a'))
print(a_s)
# attrs
a = soup.find(attrs={"id": re.compile('link')})
print(a)
# - 列表过滤器
# 列表内的数据匹配
print(soup.find(name=['a', 'p', 'html', re.compile('a')]))
print(soup.find_all(name=['a', 'p', 'html', re.compile('a')]))
# - bool过滤器
# True匹配
print(soup.find(name=True, attrs={"id": True}))
# - 方法过滤器
# 用于一些要的属性以及不需要的属性查找。
def have_id_not_class(tag):
# print(tag.name)
if tag.name == 'p' and tag.has_attr("id") and not tag.has_attr("class"):
return tag
# print(soup.find_all(name=函数对象))
print(soup.find_all(name=have_id_not_class))
# 补充知识点:
# id
a = soup.find(id='link2')
print(a)
# class
p = soup.find(class_='sister')
print(p)
