day03 (crawling Jingdong product information, parsing library)

1. crawling commodity information jingdong

Functions: search for "Murphy's Law" will be crawling all product information on Jingdong, after the completion of a crawling crawling Next until all information has been crawling

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
import time
def get_good(driver):
    number = 1
    try:
        time.sleep(5)
        js_code='''
                window.scrollTo(0,5000)
        '''
        driver.execute_script(js_code)
        time.sleep(5)
        good_list = driver.find_elements_by_class_name('gl-item')
        for good in good_list:
            good_name = good.find_element_by_css_selector('.p-name em').text
            good_url = good.find_element_by_css_selector('.p-name a').get_attribute('href')
            good_price = good.find_element_by_class_name('p-price').text
            good_commit = good.find_element_by_class_name('p-commit').text
            good_content = f'' ' 
            Number: {number} 
            Product Name: {good_name} 
            product link: {good_url} 
            commodity prices: {good_price} 
            product reviews: good_commit} { 
            \ n- 
            ' '' 
            Print (good_content) 
            with Open ( ' jd3.text ' , ' A ' , encoding = ' UTF-. 8 ' ) AS F: 
                f.write (good_content) 
            Number + =. 1
         Print ( " commodity information written successfully !! " ) 
        next_tag = driver.find_element_by_class_name ( 'pn-next')
        next_tag.click()
        time.sleep(5)
        get_good(driver)
    finally:
        driver.close()
if __name__ == '__main__':
    driver=webdriver.Chrome()
    try:
        driver.implicitly_wait(10)
        driver.get('https://www.jd.com/')
        input_tag = driver.find_element_by_id('key')
        input_tag.send_keys('墨菲定律')
        input_tag.send_keys(Keys.ENTER)
        get_good(driver)
    finally:
        driver.close()

Partial results show screenshots:

2. The element dragged to a location at a specified

2.1 instant drag

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver import  ActionChains
import time
driver=webdriver.Chrome()
try:
    driver.implicitly_wait(10)
    driver.get('https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
    time.sleep(5)
    driver.switch_to.frame('iframeResult')
    time.sleep(1)
    source = driver.find_element_by_id('draggable')
    target = driver.find_element_by_id('droppable')
    ActionChains(driver).drag_and_drop(source,target).perform()
    time.sleep(10)
finally:
    driver.close()

2.2 slow-moving

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver import  ActionChains
import time
driver=webdriver.Chrome()
try:
    driver.implicitly_wait(10)
    driver.get('https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
    time.sleep(5)
    driver.switch_to.frame('iframeResult')
    time.sleep(1)
    source = driver.find_element_by_id('draggable')
    target = driver.find_element_by_id('droppable')
    distance = target.location['x']-source.location['x']
    ActionChains(driver).click_and_hold(source).perform()
    s=0
    while s<distance:
        ActionChains(driver).move_by_offset(xoffset=5,yoffset=0).perform()
        s+=5
        time.sleep(0.1)
    ActionChains(driver).release().perform()
    time.sleep(10)
finally:
    driver.close()

3.BeautifulSoup4

html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="sister"><b>$37</b></p>

<p class="story" id="p">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" >Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
"""
from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc,'lxml')
#1. Direct use 
# Print (soup.html) 
# Print (of the type (soup.html)) 
# Print (soup.a) 
# Print (soup.p) 
# 2. obtain a name tag 
# Print (soup.a.name ) 
# property tag 3. Get 
# Print (soup.a.attrs) 
# Print (soup.a.attrs [ 'the href']) 
# Print (soup.a.attrs [ 'class']) 
# 4. Get tag text content 
# Print (soup.p.text) 
# 5. the nested selection 
# Print (soup.html.body.p) 
# 6. the child node, descendant node 
# Print (soup.p.children) # returns an iterator Object 
# Print (List (soup.p.children)) 
# 7. parent, ancestor node
# print(soup.b.parent)
# print(soup.b.parents)
# print(list(soup.b.parents))

to sum up:

find: a first look

find_all: find all

name --- name tag

attrs ----- property to find a match

text-matching text -----

label:

------ global string matching filter string

Regular filters ------

re matching module

------ List Filter

Data matching in the list

------ bool filter

True match

Filter Method ------

For some properties and do not need to look for properties

Attributes:

-clas-

-id-

day03 (crawling Jingdong product information, parsing library)

Guess you like