import requests
from bs4 import BeautifulSoup
import csv
from itertools import zip_longest
job_title = []
company_name = []
location_name = []
job_skill = []
links = []
salary = []
result = requests.get("https://wuzzuf.net/search/jobs/?q=python\&a=hpb")
source = result.content
soup = BeautifulSoup(source, "lxml")
job_titles = soup.find_all("h2", {"class": "css-m604qf"})
company_names = soup.find_all("a", {"class": "css-17s97q8"})
location_names = soup.find_all("span", {"class": "css-5wys0k"})
job_skills = soup.find_all("div", {"class": "css-y4udm8"})
for i in range(len(job_titles)):
job_title.append(job_titles[i].text)
links.append("https://wuzzuf.net" job_titles[i].find("a").attrs["href"])
company_name.append(company_names[i].text)
location_name.append(location_names[i].text)
job_skill.append(job_skills[i].text)
for link in links:
result = requests.get(link)
source = result.content
soup = BeautifulSoup(source, "lxml")
salaries = soup.find("span", {"class": "css-4xky9y"})
salary.append(salaries)
file_list = [job_title, company_name, location_name, job_skill, links, salary]
exported = zip_longest(*file_list)
with open("/Users/Rich/Desktop/JobTutorial.csv", "w") as myfile:
writer = csv.writer(myfile)
writer.writerow(["Job titles", "Company names", "Location names", "Job skills", "Links", "Salary"])
writer.writerows(exported)
print(salary)
問題是薪水函式什么都不回傳，當我將它的結果附加到一個名為薪水的串列并列印出結果時，它列印了一個無串列...
[無，無，無，無，無，無，無，無，無，無，無，無，無，無，無，無]
請幫助我，感謝您的幫助。
uj5u.com熱心網友回復：
工資資料是動態生成的，如果您檢查職位發布的源代碼/頁面源（Chrome 上的 ctrl U），您可以看到資料不在 HTML 元素中。但它可以在物件<script>內的標簽下找到Wuzzuf.initialStoreState
現在您必須決議此 json 檔案以獲取作業詳細資訊資料。你可以使用正則運算式來做到這一點
這是一個作業代碼，用于從該串列中決議單個作業的字典 -
link = "https://wuzzuf.net/jobs/p/jITGU1cOLq2S-Senior-Python-Developer-SURE-International-Technology-Cairo-Egypt"
result = requests.get(link, headers=headers)
raw_data = re.compile(r'Wuzzuf.initialStoreState = (.*);').search(result.text)
job_details_dict = json.loads(raw_data.group(1).strip())
job_details_dict
樣本輸出 -
{'badges': {'landingPage': {'loading': False,
'providers': None,
'timestamp': None}},
'browsingPage': {'sets': {}},
'coaches': {'coachesContactUs': {}, 'coachesPartner': {}},
.................
現在你只需要從這個字典中決議你想要的資料（例如薪水）
轉載請註明出處，本文鏈接：https://www.uj5u.com/net/480826.html