baidu_serpapi_scrape_organic_results

baidu_serpapi_get_organic_results.py

import os, json
from serpapi import BaiduSearch

def get_organic_results():
    params = {
        "engine": "baidu",
        "q": "minecraft",
        "api_key": os.getenv("API_KEY"),
    }

    search = BaiduSearch(params)
    results = search.get_dict()

    baidu_data = []

    for result in results['organic_results']:
      title = result['title']
      link = result['link']
      try:
        displayed_link = result['displayed_link']
      except:
        displayed_link = None
      try:
        snippet = result['snippet']
      except:
        snippet = None
      try:
        sitelink_title = result['rich_snippet']['sitelinks']['title']
      except:
        sitelink_title = None
      try:
        sitelink_link = result['rich_snippet']['sitelinks']['link']
      except:
        sitelink_link = None

      baidu_data.append({
        'title': title,
        'link': link,
        'displayed_link': displayed_link,
        'snippet': snippet,
        'sitelinks': [{'title': sitelink_title, 'link':sitelink_link}],
      })

    print(json.dumps(baidu_data, indent=2, ensure_ascii=False))

# Part of the output:
'''
[
  {
    "title": "minecraft website - 官方网站 | Minecraft",
    "link": "http://www.baidu.com/link?url=OD7rfRPzLty76yZJ9dimCAV2VS-QyXURXbLmjXH3wq3",
    "displayed_link": "minecraft.net/",
    "snippet": "我的世界是一款堆方块、不断冒险的游戏。在此购买,或浏览网站了解最新消息和社区的精彩创意!",
    "sitelinks": [
      {
        "title": null,
        "link": null
      }
    ]
  }
]
'''