Python爬虫实战：快手数据采集与舆情分析

import requests
import json

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

# 构造代理URL（格式：http://用户名:密码@代理服务器:端口）
proxyUrl = f"http://{proxyUser}:{proxyPass}@{proxyHost}:{proxyPort}"

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"
}

def fetch_kuaishou_videos(keyword="科技"):
    url = f"https://www.kuaishou.com/search/video?keyword={keyword}"
    
    # 设置代理
    proxies = {
        "http": proxyUrl,
        "https": proxyUrl,
    }
    
    try:
        response = requests.get(url, headers=headers, proxies=proxies, timeout=10)
        
        if response.status_code == 200:
            data = response.json()  # 假设返回的是JSON数据
            videos = data.get("data", {}).get("videos", [])
            for video in videos:
                print(f"标题: {video['title']}, 播放量: {video['play_count']}")
        else:
            print("请求失败:", response.status_code)
    except requests.exceptions.RequestException as e:
        print("请求异常:", e)

fetch_kuaishou_videos()

from selenium import webdriver
from selenium.webdriver.common.by import By
import time

driver = webdriver.Chrome()
driver.get("https://www.kuaishou.com")

# 模拟搜索
search_box = driver.find_element(By.CSS_SELECTOR, "input.search-input")
search_box.send_keys("科技")
search_box.submit()

time.sleep(3)  # 等待加载

# 获取视频列表
videos = driver.find_elements(By.CSS_SELECTOR, "div.video-item")
for video in videos:
    title = video.find_element(By.CSS_SELECTOR, "h3.title").text
    play_count = video.find_element(By.CSS_SELECTOR, "span.play-count").text
    print(f"标题: {title}, 播放量: {play_count}")

driver.quit()

import pandas as pd

data = [
    {"title": "Python教程", "play_count": "10万"},
    {"title": "AI技术", "play_count": "5万"}
]

df = pd.DataFrame(data)
df.to_csv("kuaishou_videos.csv", index=False)

import jieba
from snownlp import SnowNLP

comments = ["这个视频很棒！", "内容一般，没什么新意"]

# 分词示例
for comment in comments:
    words = jieba.cut(comment)
    print("/".join(words))

# 情感分析（0~1，越接近1表示越正面）
for comment in comments:
    sentiment = SnowNLP(comment).sentiments
    print(f"评论: {comment}, 情感得分: {sentiment:.2f}")

import matplotlib.pyplot as plt
from wordcloud import WordCloud

# 词云生成
text = " ".join(comments)
wordcloud = WordCloud(font_path="simhei.ttf").generate(text)
plt.imshow(wordcloud, interpolation="bilinear")
plt.axis("off")
plt.show()

# 情感分布
sentiments = [SnowNLP(c).sentiments for c in comments]
plt.hist(sentiments, bins=10, color="skyblue")
plt.xlabel("情感得分")
plt.ylabel("评论数量")
plt.title("快手评论情感分析")
plt.show()