大数据岗位技能需求挖掘：Python爬虫与NLP技术结合

import requests
from bs4 import BeautifulSoup
import pandas as pd
import time

# 代理配置
proxyHost = "www.16yun.cn"
proxyPort = "5445"
proxyUser = "16QMSOML"
proxyPass = "280651"

# 代理设置
proxyMeta = f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"
proxies = {
    "http": proxyMeta,
    "https": proxyMeta,
}

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36",
    "Proxy-Authorization": f"Basic {proxyUser}:{proxyPass}"  # 部分代理可能需要此头部
}

def fetch_jobs(keyword="大数据", page=1):
    url = f"https://www.lagou.com/jobs/list_{keyword}/p-{page}?&filterOption=3"
    try:
        response = requests.get(url, headers=headers, proxies=proxies, timeout=10)
        response.raise_for_status()  # 检查请求是否成功
        soup = BeautifulSoup(response.text, 'html.parser')
        jobs = []
        
        for item in soup.select(".item__10RTO"):
            title = item.select_one(".p-top__1F7CL a").text.strip()
            company = item.select_one(".company-name__2-SjF").text.strip()
            salary = item.select_one(".money__3Lkgq").text.strip()
            jd = item.select_one(".job-desc__3UqDp").text.strip()
            jobs.append({
                "title": title,
                "company": company,
                "salary": salary,
                "jd": jd
            })
        return jobs
    except Exception as e:
        print(f"请求失败: {e}")
        return []

# 爬取5页数据
all_jobs = []
for page in range(1, 6):
    print(f"正在爬取第 {page} 页...")
    jobs = fetch_jobs(page=page)
    if jobs:  # 只有成功获取数据时才添加
        all_jobs.extend(jobs)
    time.sleep(5)  # 增加延迟，降低被封风险

# 存储为CSV
if all_jobs:  # 检查是否有数据
    df = pd.DataFrame(all_jobs)
    df.to_csv("big_data_jobs.csv", index=False)
    print(f"数据爬取完成！共获取 {len(all_jobs)} 条数据。")
else:
    print("未能获取任何数据，请检查网络或代理设置。")

import pandas as pd

df = pd.read_csv("big_data_jobs.csv")
df.drop_duplicates(inplace=True)  # 去重
df.dropna(inplace=True)  # 去除空值
print(f"有效岗位数: {len(df)}")

import jieba
from sklearn.feature_extraction.text import TfidfVectorizer

# 加载停用词
stopwords = set()
with open("stopwords.txt", "r", encoding="utf-8") as f:
    for line in f:
        stopwords.add(line.strip())

# 分词函数
def cut_text(text):
    words = jieba.lcut(text)
    return [word for word in words if word not in stopwords and len(word) > 1]

# 对所有JD进行分词
corpus = df["jd"].tolist()
words_list = [" ".join(cut_text(jd)) for jd in corpus]

# 计算TF-IDF
tfidf = TfidfVectorizer(max_features=100)
tfidf_matrix = tfidf.fit_transform(words_list)
feature_names = tfidf.get_feature_names_out()

# 获取最重要的技能词
word_importance = {}
for i, word in enumerate(feature_names):
    word_importance[word] = tfidf_matrix[:, i].sum()

sorted_skills = sorted(word_importance.items(), key=lambda x: x[1], reverse=True)[:20]
print("Top 20 技能关键词：")
for skill, score in sorted_skills:
    print(f"{skill}: {score:.2f}")

from wordcloud import WordCloud
import matplotlib.pyplot as plt

# 生成词云
word_freq = {k: v for k, v in word_importance.items() if v > 0.1}
wc = WordCloud(font_path="simhei.ttf", background_color="white", width=800, height=600)
wc.generate_from_frequencies(word_freq)

plt.figure(figsize=(10, 8))
plt.imshow(wc, interpolation="bilinear")
plt.axis("off")
plt.title("大数据岗位技能关键词云图", fontsize=16)
plt.show()