File size: 12,726 Bytes
0a7e81a 0e9e349 0a7e81a 0e9e349 0a7e81a 0e9e349 0a7e81a 0e9e349 0a7e81a 0e9e349 0a7e81a 0e9e349 0a7e81a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 | """
Trends Client - PyTrends Wrapper
Provides Google Trends and YouTube Trends data
"""
import logging
from typing import Optional, List, Dict
from pytrends.request import TrendReq
import pandas as pd
logger = logging.getLogger(__name__)
class TrendsClient:
"""
Client for Google Trends data using pytrends.
Features:
- Trending Now (daily trends)
- Related Topics
- Related Queries
- YouTube Trends
"""
# Category codes
CATEGORIES = {
"all": 0,
"arts_entertainment": 3,
"autos_vehicles": 47,
"beauty_fitness": 44,
"books_literature": 22,
"business_industrial": 12,
"computers_electronics": 5,
"finance": 7,
"food_drink": 71,
"games": 8,
"health": 45,
"hobbies_leisure": 65,
"home_garden": 11,
"internet_telecom": 13,
"jobs_education": 958,
"law_government": 19,
"news": 16,
"online_communities": 299,
"people_society": 14,
"pets_animals": 66,
"real_estate": 29,
"reference": 533,
"science": 174,
"shopping": 18,
"sports": 20,
"travel": 67,
}
# Timeframe options
TIMEFRAMES = {
"now_1h": "now 1-H",
"now_4h": "now 4-H",
"now_1d": "now 1-d",
"now_7d": "now 7-d",
"today_1m": "today 1-m",
"today_3m": "today 3-m",
"today_12m": "today 12-m",
"today_5y": "today 5-y",
}
def __init__(self, hl: str = "en-US", tz: int = 360):
"""
Initialize TrendsClient.
Args:
hl: Host language
tz: Timezone offset
"""
self.hl = hl
self.tz = tz
self.pytrends = TrendReq(hl=hl, tz=tz)
def get_trending_now(
self,
country: str = "united_states",
limit: int = 20
) -> List[Dict]:
"""
Get currently trending searches using Google Trends RSS feed.
More reliable than pytrends API for daily trends.
Args:
country: Country code (e.g., 'united_states', 'bangladesh', 'india')
limit: Number of results (default 20)
Returns:
List of trending topics with rank
"""
import requests
import xml.etree.ElementTree as ET
# Country code mapping for RSS
country_codes = {
"united_states": "US",
"united_kingdom": "GB",
"india": "IN",
"bangladesh": "BD",
"japan": "JP",
"germany": "DE",
"france": "FR",
"brazil": "BR",
"canada": "CA",
"australia": "AU",
}
geo = country_codes.get(country, "US")
try:
# Google Trends RSS Feed URL
rss_url = f"https://trends.google.com/trending/rss?geo={geo}"
response = requests.get(rss_url, timeout=10)
response.raise_for_status()
# Parse XML
root = ET.fromstring(response.content)
results = []
items = root.findall('.//item')
for i, item in enumerate(items[:limit]):
title = item.find('title')
traffic = item.find('{https://trends.google.com/trending/rss}approx_traffic')
if title is not None:
results.append({
"rank": i + 1,
"topic": title.text,
"country": country,
"traffic": traffic.text if traffic is not None else "N/A"
})
logger.info(f"Got {len(results)} trending topics for {country} via RSS")
return results
except Exception as e:
logger.error(f"Error getting trending searches via RSS: {e}")
# Fallback to pytrends
try:
df = self.pytrends.trending_searches(pn=country)
results = []
for i, topic in enumerate(df[0].head(limit).tolist()):
results.append({
"rank": i + 1,
"topic": topic,
"country": country,
"traffic": "N/A"
})
logger.info(f"Got {len(results)} trending topics via pytrends fallback")
return results
except Exception as e2:
logger.error(f"Fallback also failed: {e2}")
return []
def get_realtime_trends(
self,
country: str = "US",
category: str = "all",
limit: int = 20
) -> List[Dict]:
"""
Get realtime trending stories.
Args:
country: Country code (US, BD, IN, etc.)
category: Category name
limit: Number of results
Returns:
List of trending stories
"""
try:
cat_code = self.CATEGORIES.get(category, 0)
df = self.pytrends.realtime_trending_searches(pn=country)
results = []
if not df.empty:
for i, row in df.head(limit).iterrows():
results.append({
"rank": i + 1,
"title": row.get('title', ''),
"entity_names": row.get('entityNames', []),
"articles": row.get('articles', [])
})
logger.info(f"Got {len(results)} realtime trends")
return results
except Exception as e:
logger.error(f"Error getting realtime trends: {e}")
return []
def get_related_topics(
self,
keyword: str,
region: str = "",
timeframe: str = "today 12-m",
category: int = 0,
search_type: str = ""
) -> Dict:
"""
Get related topics for a keyword.
Args:
keyword: Search keyword
region: Region code (empty for worldwide)
timeframe: Time range
category: Category code
search_type: 'youtube', 'news', 'images', 'froogle' or '' for web
Returns:
Dict with 'top' and 'rising' topics
"""
try:
self.pytrends.build_payload(
kw_list=[keyword],
cat=category,
timeframe=timeframe,
geo=region,
gprop=search_type
)
data = self.pytrends.related_topics()
result = {
"keyword": keyword,
"top": [],
"rising": []
}
if keyword in data:
topic_data = data[keyword]
# Top topics
if 'top' in topic_data and topic_data['top'] is not None:
top_df = topic_data['top']
for _, row in top_df.iterrows():
result["top"].append({
"topic": row.get('topic_title', ''),
"type": row.get('topic_type', ''),
"value": int(row.get('value', 0))
})
# Rising topics
if 'rising' in topic_data and topic_data['rising'] is not None:
rising_df = topic_data['rising']
for _, row in rising_df.iterrows():
result["rising"].append({
"topic": row.get('topic_title', ''),
"type": row.get('topic_type', ''),
"value": str(row.get('value', ''))
})
# Sort by value
result["top"] = sorted(result["top"], key=lambda x: x["value"], reverse=True)
logger.info(f"Got {len(result['top'])} top and {len(result['rising'])} rising topics")
return result
except Exception as e:
logger.error(f"Error getting related topics: {e}")
return {"keyword": keyword, "top": [], "rising": [], "error": str(e)}
def get_related_queries(
self,
keyword: str,
region: str = "",
timeframe: str = "today 12-m",
category: int = 0,
search_type: str = ""
) -> Dict:
"""
Get related queries for a keyword.
Args:
keyword: Search keyword
region: Region code (empty for worldwide)
timeframe: Time range
category: Category code
search_type: 'youtube', 'news', 'images', 'froogle' or '' for web
Returns:
Dict with 'top' and 'rising' queries
"""
try:
self.pytrends.build_payload(
kw_list=[keyword],
cat=category,
timeframe=timeframe,
geo=region,
gprop=search_type
)
data = self.pytrends.related_queries()
result = {
"keyword": keyword,
"top": [],
"rising": []
}
if keyword in data:
query_data = data[keyword]
# Top queries
if 'top' in query_data and query_data['top'] is not None:
top_df = query_data['top']
for _, row in top_df.iterrows():
result["top"].append({
"query": row.get('query', ''),
"value": int(row.get('value', 0))
})
# Rising queries
if 'rising' in query_data and query_data['rising'] is not None:
rising_df = query_data['rising']
for _, row in rising_df.iterrows():
result["rising"].append({
"query": row.get('query', ''),
"value": str(row.get('value', ''))
})
# Sort by value
result["top"] = sorted(result["top"], key=lambda x: x["value"], reverse=True)
logger.info(f"Got {len(result['top'])} top and {len(result['rising'])} rising queries")
return result
except Exception as e:
logger.error(f"Error getting related queries: {e}")
return {"keyword": keyword, "top": [], "rising": [], "error": str(e)}
def keyword_research(
self,
keyword: str,
region: str = "",
timeframe: str = "today 12-m",
category: str = "all",
search_type: str = "web"
) -> Dict:
"""
Complete keyword research - combines related topics and queries.
Args:
keyword: Search keyword
region: Region code (empty for worldwide)
timeframe: Time range key
category: Category name
search_type: 'web', 'youtube', 'news', 'images', 'shopping'
Returns:
Combined dict with topics and queries
"""
# Convert params
cat_code = self.CATEGORIES.get(category, 0)
tf = self.TIMEFRAMES.get(timeframe, "today 12-m")
gprop = "" if search_type == "web" else search_type
# Get both
topics = self.get_related_topics(keyword, region, tf, cat_code, gprop)
queries = self.get_related_queries(keyword, region, tf, cat_code, gprop)
return {
"keyword": keyword,
"region": region if region else "worldwide",
"timeframe": timeframe,
"category": category,
"search_type": search_type,
"related_topics": topics,
"related_queries": queries
}
def get_youtube_trends(
self,
keyword: str,
region: str = "",
timeframe: str = "today 12-m"
) -> Dict:
"""
Get YouTube-specific trends for a keyword.
"""
return self.keyword_research(
keyword=keyword,
region=region,
timeframe=timeframe,
category="all",
search_type="youtube"
)
|