Spaces:
Sleeping
Sleeping
File size: 6,035 Bytes
caa28a1 |
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 |
import requests
from bs4 import BeautifulSoup
import streamlit as st
from urllib.parse import quote
@st.cache_resource
def display_glossary_entity(k):
search_urls = {
"🚀🌌ArXiv": lambda k: f"https://arxiv.org/search/?query={quote(k)}&searchtype=all&source=header",
"📖Wiki": lambda k: f"https://en.wikipedia.org/wiki/{quote(k)}",
"🔍Google": lambda k: f"https://www.google.com/search?q={quote(k)}",
"🔎Bing": lambda k: f"https://www.bing.com/search?q={quote(k)}",
"🎥YouTube": lambda k: f"https://www.youtube.com/results?search_query={quote(k)}",
"🐦Twitter": lambda k: f"https://twitter.com/search?q={quote(k)}",
}
links_md = ' '.join([f"[{emoji}]({url(k)})" for emoji, url in search_urls.items()])
st.markdown(f"**{k}** <small>{links_md}</small>", unsafe_allow_html=True)
def perform_search(search_query, search_engine):
if search_engine == "Google":
url = f"https://www.google.com/search?q={search_query}"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
html_content = soup.prettify()
text_content = soup.get_text()
links = [link["href"] for link in soup.find_all("a", href=True)]
images = [img["src"] for img in soup.find_all("img", src=True)]
results = {
"html": html_content,
"text": text_content,
"links": links,
"images": images
}
elif search_engine == "Bing":
url = f"https://www.bing.com/search?q={search_query}"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
html_content = soup.prettify()
text_content = soup.get_text()
links = [link["href"] for link in soup.find_all("a", href=True)]
images = [img["src"] for img in soup.find_all("img", src=True)]
results = {
"html": html_content,
"text": text_content,
"links": links,
"images": images
}
elif search_engine == "Wikipedia":
url = f"https://en.wikipedia.org/w/index.php?search={search_query}"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
html_content = soup.prettify()
text_content = soup.get_text()
links = [link["href"] for link in soup.find_all("a", href=True)]
images = [img["src"] for img in soup.find_all("img", src=True)]
results = {
"html": html_content,
"text": text_content,
"links": links,
"images": images
}
elif search_engine == "Twitter":
url = f"https://twitter.com/search?q={search_query}"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")
html_content = soup.prettify()
text_content = soup.get_text()
links = [link["href"] for link in soup.find_all("a", href=True)]
images = [img["src"] for img in soup.find_all("img", src=True)]
results = {
"html": html_content,
"text": text_content,
"links": links,
"images": images
}
return results
def main():
st.set_page_config(page_title="Web Search App", page_icon=":mag:", layout="wide")
st.title("Web Search App")
st.write("Search Google, Bing, Wikipedia, and Twitter simultaneously!")
search_query = st.text_input("Enter your search query")
display_glossary_entity(search_query)
col1, col2, col3, col4 = st.columns(4)
with col1:
st.header("Google Search Results")
if st.button("Search Google"):
google_results = perform_search(search_query, "Google")
st.write("HTML Content:")
st.code(google_results["html"], language="html")
st.write("Text Content:")
st.write(google_results["text"])
st.write("Links:")
for link in google_results["links"]:
st.write(link)
st.write("Images:")
for image in google_results["images"]:
st.image(image)
with col2:
st.header("Bing Search Results")
if st.button("Search Bing"):
bing_results = perform_search(search_query, "Bing")
st.write("HTML Content:")
st.code(bing_results["html"], language="html")
st.write("Text Content:")
st.write(bing_results["text"])
st.write("Links:")
for link in bing_results["links"]:
st.write(link)
st.write("Images:")
for image in bing_results["images"]:
st.image(image)
with col3:
st.header("Wikipedia Search Results")
if st.button("Search Wikipedia"):
wikipedia_results = perform_search(search_query, "Wikipedia")
st.write("HTML Content:")
st.code(wikipedia_results["html"], language="html")
st.write("Text Content:")
st.write(wikipedia_results["text"])
st.write("Links:")
for link in wikipedia_results["links"]:
st.write(link)
st.write("Images:")
for image in wikipedia_results["images"]:
st.image(image)
with col4:
st.header("Twitter Search Results")
if st.button("Search Twitter"):
twitter_results = perform_search(search_query, "Twitter")
st.write("HTML Content:")
st.code(twitter_results["html"], language="html")
st.write("Text Content:")
st.write(twitter_results["text"])
st.write("Links:")
for link in twitter_results["links"]:
st.write(link)
st.write("Images:")
for image in twitter_results["images"]:
st.image(image)
if __name__ == "__main__":
main() |