def login():
# Login via Wechat
browser.get("https://passport.jd.com/uc/login?ltype=logout&ReturnUrl=https://global.jd.com/")
time.sleep(2)
if browser.find_element_by_link_text("微信"):
browser.find_element_by_link_text("微信").click()
print("Please login within 6 sec")
time.sleep(6)
def openurl(url, num):
browser = webdriver.Chrome() #打开浏览器
browser.get(url) #进入相关网站
html = browser.page_source #获取网站源码
data = str(pq(html)) #str() 函数将对象转化为适于人阅读的形式。
print(data)
dic = {}
re_rule = r'<div class="news-item-container">(.*?)<div data-v-00b2e9bc=""/>'
datalist = re.findall(re_rule, data, re.S)
for i in range(0, len(datalist)):
rule1 = r'<img src="/img/icon-lihao.png" data-v-6c26747a=""/>(.*?)<!----></span>'
bullish = re.findall(rule1, datalist[i], re.S)
if len(bullish) == 0:
rule1 = r'<img src="/img/icon-likong.png" data-v-6c26747a=""/>(.*?)</span>'
bullish = re.findall(rule1, datalist[i], re.S)
rule2 = r'<span class="stock-group-item-name" data-v-f97d9694="">(.*?)</span>'
stock_name = re.findall(rule2, datalist[i], re.S)
if len(stock_name) > 0 and len(bullish) > 0:
for c in range(0, len(stock_name)):
dic[stock_name[c]] = bullish[0]
print("正在爬取第", len(dic) + 1, "个请稍等.....")
c = len(datalist)
if len(dic) < num:
while (1):
browser.find_element_by_class_name("home-news-footer").click()
time.sleep(1)
html = browser.page_source
data = str(pq(html))
datalist = re.findall(re_rule, data, re.S)
for i in range(c, len(datalist)):
rule3 = r'<img data-v-6c26747a="" src="/img/icon-lihao.png"/>(.*?)<!----></span>'
bullish = re.findall(rule3, datalist[i], re.S)
if len(bullish) == 0:
rule5 = r'<img data-v-6c26747a="" src="/img/icon-likong.png"/>(.*?)</span>'
bullish = re.findall(rule5, datalist[i], re.S)
rule4 = r'<span data-v-f97d9694="" class="stock-group-item-name">(.*?)</span>'
stock_name = re.findall(rule4, datalist[i], re.S)
if len(stock_name) > 0 and len(bullish) > 0:
for c in range(0, len(stock_name)):
dic[stock_name[c]] = bullish[0]
c = len(datalist)
if len(dic) > num:
browser.quit()
print("爬取完毕！！")
break
print("正在爬取第", len(dic) + 1, "个请稍等.....")
else:
browser.quit()
print("爬取完毕！！")
return dic
def getDate():
# 3.发送请求
browser.get(url)
# 4.定位全国
browser.find_element_by_css_selector("#changeCityBox > p.checkTips > a").click()
# 5.找到文本框输入数据分析
browser.find_element_by_css_selector("#search_input").send_keys("数据分析")
# 6.找到搜索按钮并点击
browser.find_element_by_css_selector("#search_button").click()
time.sleep(3)
# 7.自动翻页 pager_next_disabled pager_next
i = 1
# 控制页数
j = 1
# 控制条数
while (browser.page_source.find('pager_next_disabled') == -1):
# 找到li
li_List = browser.find_elements_by_css_selector("#s_position_list > ul > li")
# 循环遍历 123456789101112131415161718192021
for li in li_List:
# 标题
title = li.find_element_by_css_selector("div.list_item_top > div.position > div.p_top > a > h3").text
# 地址
address = \
li.find_element_by_css_selector("div.list_item_top > div.position > div.p_top > a > span > em").text.split(
"·")[0]
# 公司
company = li.find_element_by_css_selector("div.list_item_top > div.company > div.company_name > a").text
# 薪水，经验
result = li.find_element_by_css_selector("div.list_item_top > div.position > div.p_bot > div").text
# 薪水
salary = result.split(" ")[0]
# 经验
exp = result.split(" ")[1].replace("经验", "")
# 学历
edu = result.split(" ")[-1]
# 类型
type = li.find_element_by_class_name("industry").text.split("/")[0].strip()
# 写入cvs
with open("lagou_date.cvs", "a", encoding="utf-8", newline="") as file:
csvWriter = csv.writer(file).writerow([title, address, company, salary, exp, edu, type])
print("第{}页第{}条下载成功".format(i, j))
j += 1
# 找到 下一页点击
browser.find_element_by_class_name("pager_next").click()
i += 1
time.sleep(3)
from selenium import webdriver
import time
import math
from idlelib import browser
link = "http://suninjuly.github.io/selects1.html"
try:
browser = webdriver.Chrome()
browser.get(link)
num1 = browser.find_element_by_id("num1")
x = num1.text
num2 = browser.find_element_by_id("num2")
y = num2.text
z = str(int(x) + int(y))
from selenium.webdriver.support.ui import Select
select = Select(browser.find_element_by_tag_name("select"))
select.select_by_value(z)
button = browser.find_element_by_css_selector("button.btn")
button.click()
finally:
time.sleep(15)
browser.quit()
def picking():
# Open your cart
browser.get("https://cart.jd.com/cart.action#none")
time.sleep(2)
