update all

science_access/enter_author_name.py

@@ -31,6 +31,9 @@ from science_access.word_cloud_by_word_len import generate_from_lengths
 from science_access.utils import check_passive
 import plotly.graph_objects as go
 
+from typing import List, Any
+import pandas as pd
+
 theme = px.colors.diverging.Portland
 colors = [theme[-1], theme[-2]]
 
@@ -211,12 +214,6 @@ def create_giant_strings(ar, not_want_list):
     return sci_corpus
 
 
-def make_clickable(link):
-    # target _blank to open new window
-    # extract clickable text to display for your link
-    text = link  # .split('=')[1]
-    return f'<a target="_blank" href="{link}">{text}</a>'
-
 
 def extra_options(ar, trainingDats, df1):
 
@@ -353,12 +350,22 @@ def grand_distribution_plot(ar, scraped_labels, standard_sci, df0, author_name="
     return df1, fig
 
 
-from typing import List, Any
-import pandas as pd
 
-# import streamlit as st
-# List
-def push_frame_to_screen(contents: Any, readability_vector: List) -> pd.DataFrame():
+
+def make_clickable(link):
+    # target _blank to open new window
+    # extract clickable text to display for your link
+    text = link  # .split('=')[1]
+    return f'<a target="_blank" href="{link}">{text}</a>'
+df_links["Web_Link"] = contents["Web_Link"]
+df_links["Reading_Level"] = contents["Reading_Level"]
+df_links.drop_duplicates(subset="Web_Link", inplace=True)
+df_links["Web_Link"] = df_links["Web_Link"].apply(make_clickable)
+df_links = df_links.to_html(escape=False)
+st.write(df_links, unsafe_allow_html=True)
+
+
+def push_frame_to_screen(contents, readability_vector):# -> pd.DataFrame():
     if type(contents) is type(list()):
         df_links = pd.DataFrame()
         df_links["Web_Link"] = pd.Series(contents)
@@ -367,19 +374,16 @@ def push_frame_to_screen(contents: Any, readability_vector: List) -> pd.DataFram
         df_links["Web_Link"] = df_links["Web_Link"].apply(make_clickable)
         df_links = df_links.to_html(escape=False)
         st.write(df_links, unsafe_allow_html=True)
-
-    if type(contents) is type(pd.DataFrame()):
+    else:
         df_links = pd.DataFrame()
-        try:
-            df_links["Web_Link"] = contents["Web_Link"]
-            df_links["Reading_Level"] = contents["Reading_Level"]
-            df_links.drop_duplicates(subset="Web_Link", inplace=True)
-            df_links["Web_Link"] = df_links["Web_Link"].apply(make_clickable)
-            df_links = df_links.to_html(escape=False)
-            st.write(df_links, unsafe_allow_html=True)
-
-        except:
-            pass
+        #try:
+        df_links["Web_Link"] = contents["Web_Link"]
+        df_links["Reading_Level"] = contents["Reading_Level"]
+        df_links.drop_duplicates(subset="Web_Link", inplace=True)
+        df_links["Web_Link"] = df_links["Web_Link"].apply(make_clickable)
+        df_links = df_links.to_html(escape=False)
+        st.write(df_links, unsafe_allow_html=True)
+
     return df_links
 
 

science_access/online_app_backend.py

@@ -17,6 +17,9 @@ from tqdm.auto import tqdm
 import streamlit as st
 from .t_analysis import text_proc
 
+import streamlit as st
+from dask import compute
+
 
 class tqdm:
     """
@@ -145,7 +148,6 @@ def semantic_scholar_alias(NAME):
                         return aliases
 
 
-import streamlit as st
 
 
 def visit_semantic_scholar_abstracts(NAME, tns, more_links):
@@ -159,28 +161,31 @@ def visit_semantic_scholar_abstracts(NAME, tns, more_links):
     dois, coauthors, titles, visit_urls = author_to_urls(NAME)
 
     for d in tqdm(dois, title="visiting abstracts"):
-        paper = sch.paper(d, timeout=8)
-
-        urlDat = {}
-        if "citationVelocity" in paper.keys():
-            urlDat["citationVelocity"] = paper["citationVelocity"]
-        if "fieldsOfStudy" in paper.keys():
-            urlDat["fieldsOfStudy"] = str(paper["fieldsOfStudy"])
-        if "numCitedBy" in paper.keys():
-            urlDat["numCitedBy"] = paper["numCitedBy"]
-        # urlDat["influentialCitationCount"] = paper["influentialCitationCount"]
-        urlDat["semantic"] = True
-
-        if "url" in paper.keys():
-            urlDat["link"] = paper["title"]
-        if aliases is None:
-            if "aliases" in paper.keys():
-                urlDat["aliases"] = paper["aliases"]
-            else:
-                pass
-        if "abstract" in paper.keys():
-            urlDat = text_proc(str(paper["abstract"]), urlDat)
-            author_results.append(urlDat)
+        try:
+            paper = sch.paper(d, timeout=16)
+
+            urlDat = {}
+            if "citationVelocity" in paper.keys():
+                urlDat["citationVelocity"] = paper["citationVelocity"]
+            if "fieldsOfStudy" in paper.keys():
+                urlDat["fieldsOfStudy"] = str(paper["fieldsOfStudy"])
+            if "numCitedBy" in paper.keys():
+                urlDat["numCitedBy"] = paper["numCitedBy"]
+            # urlDat["influentialCitationCount"] = paper["influentialCitationCount"]
+            urlDat["semantic"] = True
+
+            if "url" in paper.keys():
+                urlDat["link"] = paper["title"]
+            if aliases is None:
+                if "aliases" in paper.keys():
+                    urlDat["aliases"] = paper["aliases"]
+                else:
+                    pass
+            if "abstract" in paper.keys():
+                urlDat = text_proc(str(paper["abstract"]), urlDat)
+                author_results.append(urlDat)
+        except:
+            pass
     author_results = [
         urlDat for urlDat in author_results if not isinstance(urlDat, type(None))
     ]
@@ -188,7 +193,6 @@ def visit_semantic_scholar_abstracts(NAME, tns, more_links):
     return author_results, visit_urls
 
 
-from dask import compute
 
 
 def visit_link_unpaywall(NAME):  # ), tns, visit_urls):