CVGenerator/scrape.py at main · henovw/CVGenerator · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
import time

class jobInfo:
    def __init__(self, jobDescription,companyDescription, title):
        self.jobDescription = jobDescription
        self.companyDescription = companyDescription
        self.title = title


def getInfo(link):
    driver = webdriver.Chrome()
    driver.get(link)


    ## FOR JOB INFO
    # x button
    xbutton = driver.find_elements(By.CLASS_NAME,'modal__dismiss')
    for element in xbutton:
        if element.aria_role == "button":
            element.click()

    # job title
    t = driver.find_element(By.CLASS_NAME, 'top-card-layout__title').text

    # show more
    driver.find_element(By.CLASS_NAME, 'show-more-less-html__button').click()

    # get description
    jobdesc = driver.find_element(By.CLASS_NAME, "show-more-less-html__markup").text


    ## FOR COMPANY INFO
    # scroll to top
    driver.execute_script("window.scrollBy(0, -10000)")

    # company page
    comp = driver.find_element(By.CLASS_NAME, 'topcard__org-name-link.topcard__flavor--black-link')
    cn = comp.text
    comp.click()

    # switch to new tab
    tabs = driver.window_handles
    driver.switch_to.window(tabs[-1])

    # x button
    xbutton = driver.find_elements(By.CLASS_NAME,'modal__dismiss')
    for element in xbutton:
        if element.aria_role == "button":
            element.click()

    # get description
    compdesc = driver.find_element(By.XPATH, '//p[@data-test-id="about-us__description"]').text

    driver.quit()

    return jobInfo(jobdesc, compdesc, t + cn)