Job_Scraper/jobup_scraper.py at main · Patrick2ooo/Job_Scraper · 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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
from bs4 import BeautifulSoup
from playwright.sync_api import sync_playwright
import traceback


def add_value(data, key, value):
    if key in data.keys():
        if type(data[key]) is list:
            data[key] = data[key] + [value]
        else:
            data[key] = [data[key]] + [value]
    else:
        data[key] = value

    return data

def jobup_scraper(url):
    with sync_playwright() as playwright:
        my_dict = {}
        browser = playwright.chromium.launch(headless=True)
        context = browser.new_context(
            user_agent=(
                "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
                "AppleWebKit/537.36 (KHTML, like Gecko) "
                "Chrome/120.0.0.0 Safari/537.36"
            )
        )
        page = context.new_page()
        page.goto(url)
        page.get_by_role("button", name="ok", exact=True).click()
        try:
            while True:
                page.wait_for_selector('a[data-cy="job-link"]')
                html = page.content()
                soup = BeautifulSoup(html, "html.parser")
                job_list = soup.find("div", {"aria-label": "Liste d'emplois"}) # Need to correct if the language change
                if not job_list:
                    raise Exception("No job found")
                all_job_name = job_list.find_all("div", {"class": "mb_s8"})
                all_company_name = job_list.find_all("div", {"class": "d_grid ai_center gap_s12 grid-tc_[auto_1fr] mt_s12"})
                all_job_id = job_list.find_all("a", {"data-cy": "job-link"})

                joblinks = page.locator('a[data-cy="job-link"]')
                count = joblinks.count()
                for i in range(count):
                    joblinks.nth(i).click()
                    page.wait_for_selector('div[data-cy="vacancy-description"]')
                    html = page.content()
                    soup = BeautifulSoup(html, "html.parser")
                    div_description = soup.find("div", {"data-cy": "vacancy-description"}, class_=lambda s: s != "mb_s24")
                    div_des = div_description.find_all("div", class_ = "mb_s24", recursive=False)
                    for div in div_des:
                        div.decompose()
                    description = ""
                    for d in div_description:
                        description += d.text.strip()
                    location = soup.find("p", {"class": "mb_s12 lastOfType:mb_s0 textStyle_body2 pt_s8"})
                    if location is None:
                        continue
                    location = location.text.strip()
                    href = all_job_id[i].get("href")
                    id_ = href[-37:len(href) - 1]
                    job_link = f"https://www.jobup.ch/fr/emplois/detail/{id_}"
                    name = all_job_name[i].text.strip()
                    name = name.replace('"', '')
                    company_name = all_company_name[i].text.strip()
                    my_dict.update({id_: f'=HYPERLINK("{job_link}","{name}")'})
                    my_dict = add_value(my_dict, id_, company_name)
                    my_dict = add_value(my_dict, id_, location)
                    my_dict = add_value(my_dict, id_, description)
                page.wait_for_timeout(1000)
                next = page.get_by_role("link", name="Suivant") # Need to correct if the language change
                if not next.is_visible():
                    break
                next.click()
                page.wait_for_timeout(1000)

        except Exception as e:
            my_dict.clear()
            my_dict.update({'ERROR in jobup script': str(e)})
            print(traceback.format_exc())
        finally:
            page.close()
            return my_dict