第1个爬虫程序：
main.py
#! python# -*- coding: utf-8 -*-from urllib.request import urlopenurl = "/"if __name__ == '__main__':resp = urlopen(url)# 把读取到网页的页面源代码写入myGetFile.html文件with open("myGetFile.html", mode="w", encoding='utf-8') as f:f.write(resp.read().decode('utf-8'))f.close() # 关闭文件resp.close() # 关闭resp响应print("结束")
第2个爬虫程序：
main2.py
# -*- coding: utf-8 -*-import requestsif __name__ == '__main__':query = input("请输入一个你喜欢的明星：")url = f"/s?ie=utf-8&f=8&rsv_bp=1&srcqid=5655130659909863611&tn=50000021_hao_pg&wd={query}"dic = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) ""Chrome/93.0.4577.63 Safari/537.36 Edg/93.0.961.47"}resp = requests.get(url, headers=dic) # 处理一个小小的反爬# print(resp)# print(resp.text) # 打印读取到的网页的页面源代码# 把读取到网页的页面源代码写入myGetFile.html文件with open("myGetFile.html", mode="w", encoding='utf-8') as f:f.write(resp.text) # 读取到网页的页面源代码f.close() # 关闭文件resp.close() # 关闭resp响应连接print("结束")
第3个爬虫程序：
main3.py
# -*- coding: utf-8 -*-import requestsif __name__ == '__main__':url = "/sug"s = input("请输入你要翻译的英文单词：")# 要翻译的英文单词dat = {"kw": s}# 用户代理dicHeaders = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) ""Chrome/93.0.4577.63 Safari/537.36 Edg/93.0.961.47"}# 发送post请求，发送的数据必须放在字典中，通过data参数进行传递resp = requests.post(url, headers=dicHeaders, data=dat)# print(resp.text)# 将服务器返回的内容直接处理成json(),就是字典格式print(resp.json())resp.close() # 关闭resp响应连接print("结束")
第4个爬虫程序：
main4.py
# -*- coding: utf-8 -*-import requestsif __name__ == '__main__':url = "/j/chart/top_list"# 参数dicParam = {"type": "24","interval_id": "100:90","action": "","start": "0","limit": "20"}# 用户代理dicHeaders = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) ""Chrome/93.0.4577.63 Safari/537.36 Edg/93.0.961.47"}# 发送get请求，发送的数据必须放在字典中，通过params参数进行传递resp = requests.get(url=url, params=dicParam, headers=dicHeaders) # 处理小小的反爬# print(resp.text)# 将服务器返回的内容直接处理成json(),就是字典格式# print(resp.json())objData = resp.json()# 打印信息for i in range(0, len(objData)):print(objData[i])resp.close() # 关闭resp响应连接print("结束")
第5个爬虫程序：
main5.py
# -*- coding: utf-8 -*-import requestsif __name__ == '__main__':url = "/j/chart/top_list"# 进行连续2轮获取数据，每轮20个数据for n in range(0, 2):# 参数dicParam = {"type": "24","interval_id": "100:90","action": "","start": f"{20*n}","limit": "20"}# 用户代理dicHeaders = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) ""Chrome/93.0.4577.63 Safari/537.36 Edg/93.0.961.47"}# 发送post请求，发送的数据必须放在字典中，通过data参数进行传递resp = requests.get(url=url, params=dicParam, headers=dicHeaders) # 处理小小的反爬# print(resp.text)# 将服务器返回的内容直接处理成json(),就是字典格式# print(resp.json())objData = resp.json()print(f"第{n+1}轮20个数据:")# 打印信息for i in range(0, len(objData)):print(objData[i])resp.close() # 关闭resp响应连接print("结束")
关注公众号，获取更多资料
