Fix bug when time series search returned more than one result pages

* bump version on setup.py

* add badges to readme

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

* Updates README.rst

*  Fix bug when time series search returned more than one result pages

* Fix bug when time series search returned more than one result pages

* Fix bug when time series search returned more than one result pages

* Fix bug when time series search returned more than one result pages

* Fix bug when time series search returned more than one result pages

* Fix bug when time series search returned more than one result pages

Author: rafpyprog

pytest.ini

@@ -8,4 +8,5 @@ markers =
     metadata
     pep8
     mypy
+    search
     ts

setup.py

@@ -1,13 +1,14 @@
 from setuptools import setup, find_packages
 
-__version__ = '2.0'
+__version__ = '2.0.1'
 
 with open('README.rst', 'r', encoding='utf-8') as f:
     readme = f.read()
 
 
 requirements = [
-    'lxml>=4.3.4',
+    'beautifulsoup4>=4.7.1',
+    'html5lib>=1.0.1',
     'pandas>=0.24.2',
     'retrying>=1.3.3',
     'requests>=2.22.0',

sgs/__version__.py

@@ -1 +1 @@
-__version__ = "2.0"
+__version__ = "2.0.1"

sgs/search.py

@@ -77,7 +77,7 @@ def parse_search_response(response, language: str) -> Optional[list]:
     LAST = cols["last"]
 
     try:
-        df = pd.read_html(HTML, attrs={"id": "tabelaSeries"}, flavor="lxml")[0]
+        df = pd.read_html(HTML, attrs={"id": "tabelaSeries"}, flavor="html5lib", skiprows=1)[0]
         df[START] = df[START].map(lambda x: to_datetime(x, language))
         df[LAST] = df[LAST].map(lambda x: to_datetime(x, language))
         col_names = {

tests/test_search.py

@@ -4,22 +4,25 @@
 from sgs.search import *
 from sgs.common import to_datetime
 
-
+@pytest.mark.search
 @pytest.mark.parametrize("language", ["en", "pt"])
 def test_init_search_session(language):
     session = init_search_session(language)
     assert isinstance(session, requests.Session)
 
 
+@pytest.mark.search
 def test_search_by_code_english():
     code = 4
     results = search_ts(code, Language.en.value)
+    print(results)
     metadata = results[0]
     assert metadata['name'] == "BM&F Gold - gramme"
     assert metadata['first_value'] == to_datetime("29/12/1989", "en")
     assert metadata['frequency'] == "D"
 
 
+@pytest.mark.search
 def test_search_by_code_portuguese():
     code = 4
     results = search_ts(code, Language.pt.value)
@@ -29,6 +32,7 @@ def test_search_by_code_portuguese():
     assert metadata['frequency'] == "D"
 
 
+@pytest.mark.search
 @pytest.mark.parametrize(
     "query,language,expected",
     [
@@ -74,6 +78,7 @@ def test_search_by_code(query, language, expected):
     assert results["first_value"] == first_value
 
 
+@pytest.mark.search
 def test_search_by_text():
     results = search_ts("Ouro BM$F - grama", "pt")
     assert isinstance(results, list)
@@ -84,6 +89,14 @@ def test_search_by_text():
     assert results is None
 
 
+@pytest.mark.search
+def test_search_by_text_query_returns_multiple_result_pages():
+    results = search_ts("produto", "pt")
+    assert isinstance(results, list)
+    assert len(results) == 50
+
+
+@pytest.mark.search
 def test_search_by_text_multiple_results():
     results = search_ts("dolar", "pt")
     assert isinstance(results, list)