Spaces:
Runtime error
Runtime error
Ashhar
commited on
Commit
·
9dfbf64
1
Parent(s):
19598a5
fixed bug with scraper'
Browse files- tools/webScraper.py +7 -4
tools/webScraper.py
CHANGED
|
@@ -3,7 +3,7 @@ from urllib.parse import parse_qs, urlparse
|
|
| 3 |
from bs4 import BeautifulSoup
|
| 4 |
import requests
|
| 5 |
from typing import TypedDict
|
| 6 |
-
import utils as U
|
| 7 |
|
| 8 |
SIMULATE_BROWSER = os.environ.get("SIMULATE_BROWSER_SEARCH") == "true"
|
| 9 |
|
|
@@ -36,7 +36,7 @@ else:
|
|
| 36 |
|
| 37 |
|
| 38 |
def scrapeGoogleSearch(query):
|
| 39 |
-
U.pprint(f"{SIMULATE_BROWSER=}")
|
| 40 |
finalResponse = []
|
| 41 |
|
| 42 |
headers = {
|
|
@@ -61,7 +61,6 @@ def scrapeGoogleSearch(query):
|
|
| 61 |
with open("soup_dump.html", "w", encoding="utf-8") as file:
|
| 62 |
file.write(soup.prettify())
|
| 63 |
|
| 64 |
-
results = soup.find("body")
|
| 65 |
mainDiv = soup.find("div", attrs={"id": "main"})
|
| 66 |
answerText = ""
|
| 67 |
if SELECTORS.get("answer"):
|
|
@@ -80,6 +79,8 @@ def scrapeGoogleSearch(query):
|
|
| 80 |
|
| 81 |
results = mainDiv.select(SELECTORS["search_results"])
|
| 82 |
resultsDesc = mainDiv.select(SELECTORS["search_results_desc"])
|
|
|
|
|
|
|
| 83 |
|
| 84 |
if results:
|
| 85 |
finalResponse.append("Search Results:\n")
|
|
@@ -91,7 +92,7 @@ def scrapeGoogleSearch(query):
|
|
| 91 |
parsedUrl = urlparse(link)
|
| 92 |
urlParams = parse_qs(parsedUrl.query)
|
| 93 |
link = urlParams.get("q", [None])[0]
|
| 94 |
-
desc = resultsDesc[i].text
|
| 95 |
finalResponse.append(f"Title: {title}")
|
| 96 |
finalResponse.append(f"Description: {desc}")
|
| 97 |
finalResponse.append(f"URL: {link}\n")
|
|
@@ -99,3 +100,5 @@ def scrapeGoogleSearch(query):
|
|
| 99 |
print("Failed to retrieve search results.")
|
| 100 |
|
| 101 |
return "\n".join(finalResponse)
|
|
|
|
|
|
|
|
|
| 3 |
from bs4 import BeautifulSoup
|
| 4 |
import requests
|
| 5 |
from typing import TypedDict
|
| 6 |
+
# import utils as U
|
| 7 |
|
| 8 |
SIMULATE_BROWSER = os.environ.get("SIMULATE_BROWSER_SEARCH") == "true"
|
| 9 |
|
|
|
|
| 36 |
|
| 37 |
|
| 38 |
def scrapeGoogleSearch(query):
|
| 39 |
+
# U.pprint(f"{SIMULATE_BROWSER=}")
|
| 40 |
finalResponse = []
|
| 41 |
|
| 42 |
headers = {
|
|
|
|
| 61 |
with open("soup_dump.html", "w", encoding="utf-8") as file:
|
| 62 |
file.write(soup.prettify())
|
| 63 |
|
|
|
|
| 64 |
mainDiv = soup.find("div", attrs={"id": "main"})
|
| 65 |
answerText = ""
|
| 66 |
if SELECTORS.get("answer"):
|
|
|
|
| 79 |
|
| 80 |
results = mainDiv.select(SELECTORS["search_results"])
|
| 81 |
resultsDesc = mainDiv.select(SELECTORS["search_results_desc"])
|
| 82 |
+
# Ensure resultsDesc has the same length as results
|
| 83 |
+
resultsDesc += [None] * (len(results) - len(resultsDesc))
|
| 84 |
|
| 85 |
if results:
|
| 86 |
finalResponse.append("Search Results:\n")
|
|
|
|
| 92 |
parsedUrl = urlparse(link)
|
| 93 |
urlParams = parse_qs(parsedUrl.query)
|
| 94 |
link = urlParams.get("q", [None])[0]
|
| 95 |
+
desc = resultsDesc[i].text if resultsDesc[i] else ""
|
| 96 |
finalResponse.append(f"Title: {title}")
|
| 97 |
finalResponse.append(f"Description: {desc}")
|
| 98 |
finalResponse.append(f"URL: {link}\n")
|
|
|
|
| 100 |
print("Failed to retrieve search results.")
|
| 101 |
|
| 102 |
return "\n".join(finalResponse)
|
| 103 |
+
|
| 104 |
+
print(scrapeGoogleSearch("kommuneity"))
|