立項背景：在做深度學習的過程中利用python進行建模，需要資料來訓練模型。專案流程圖
原始碼
from selenium.webdriver import chrome #引入selenium中的chrome
from selenium.webdriver.common.keys import keys #引入鍵盤
import time #時間模組
import requests
import os
import csv
import codecs
import csv
data_index=
1data=[1
,2,3
,4,5
]temp_index1=
1temp_index2=
1browser=chrome(
)#建立瀏覽器
browser.get(
"")browser.find_element_by_id(
'btn2'
).click(
)#找到輸入框，輸入**並且回車
time.sleep(3)
js="var q=document.documentelement.scrolltop=10000"
browser.execute_script(js)
time.sleep(3)
browser.find_element_by_xpath(
'//div[@class="detail-cont-top"]//*[@type="text"]'
).send_keys(
"製造業"
,keys.enter)
browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[1]/div[2]/div[1]/div[1]/div/i'
).click(
)lis=browser.find_elements_by_xpath(
'//*[@id="result_a"]/ul//li[@class="tree-empty tree-opened"]'
)for li in lis[11:
13]: src_name=li.find_element_by_xpath(
'.//a'
).get_attribute(
"data-name"
)print
(src_name)
path=
'f:\\pang'
+'\\'
+src_name
i***ists = os.path.exists(path)
ifnot i***ists:
os.makedirs(path)
#爬資料_第二個框
li.find_element_by_xpath(
'.//a'
).click(
) browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[1]/div[2]/div[2]/div[1]/div[1]/label/i'
).click(
) browser.find_element_by_xpath(
'//div[@class="arrow-btns"]/button[1]'
).click(
)print
("手點"
) time.sleep(10)
browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[1]/div[2]/div[2]/div[3]/div[1]/label/i'
).click(
) browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[2]/div[2]/div[1]/div[3]/ul/li[1]/label/i'
).click(
) browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[2]/div[2]/div[1]/div[3]/ul/li[3]/label/i'
).click(
) browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[2]/div[2]/div[1]/div[3]/ul/li[15]/label/i'
).click(
) browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[2]/div[2]/div[1]/div[3]/ul/li[16]/label/i'
).click(
) browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[2]/div[2]/div[2]/button[1]'
).click(
) browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/div[2]/div[2]/div[2]/div[3]/div[1]/label/i'
).click(
) browser.find_element_by_xpath(
'//*[@id="root"]/div/div[3]/div/div/div/div[1]/div/button'
).click(
)#頁面出來了
for page_index in
range
(200):
for i in
range(10
):for j in
range(4
):temp=
'//*[@id="contenttable"]/tbody/tr['
+str
(i+1)+
']/td['
+str
(j+1)+
']' browser.execute_script(js)
time.sleep(3)
data_1=browser.find_element_by_xpath(temp)
.get_attribute(
'title'
) data[0]
=data_index
data[j+1]
=data_1
data_index+=
1print
(data)
path_new = path +
'\\data.csv'
with
open
(path_new,
'a',encoding=
'utf-8'
,newline='')
as csvfile:
writer = csv.writer(csvfile)
writer.writerow(data)
print
(page_index+1,
) browser.find_element_by_xpath(
'//li[@class="page-next"]'
).click(
)
time.sleep(
10)
專案執行效果selenium 爬取拉勾
用到的知識點 用selenium爬取拉勾 from lxml import etree from selenium import webdriver from selenium.webdriver.support import expected conditions as ec from selen...
selenium爬取拉勾
用到的知識點 用selenium爬取拉勾 from lxml import etree from selenium import webdriver from selenium.webdriver.support import expected conditions as ec from selen...
selenium爬取京東商品
from selenium import webdriver import time import pandas as pd url browser webdriver.chrome browser.get url 找到頁面中的搜尋框，然後輸入想找的商品 browser.find element b...