Merge pull request #282 from jkawamoto/kwargs

Pass optional arguments to requests.get

newsplease/__init__.py

@@ -111,26 +111,26 @@ def from_html(html, url=None, download_date=None, fetch_images=True):
         return final_article
 
     @staticmethod
-    def from_url(url, timeout=None, user_agent=None):
+    def from_url(url, request_args=None):
         """
         Crawls the article from the url and extracts relevant information.
         :param url:
-        :param timeout: in seconds, if None, the urllib default is used
+        :param request_args: optional arguments that `request` takes
         :return: A NewsArticle object containing all the information of the article. Else, None.
         :rtype: NewsArticle, None
         """
-        articles = NewsPlease.from_urls([url], timeout=timeout, user_agent=user_agent)
+        articles = NewsPlease.from_urls([url], request_args=request_args)
         if url in articles.keys():
             return articles[url]
         else:
             return None
 
     @staticmethod
-    def from_urls(urls, timeout=None, user_agent=None):
+    def from_urls(urls, request_args=None):
         """
         Crawls articles from the urls and extracts relevant information.
         :param urls:
-        :param timeout: in seconds, if None, the urllib default is used
+        :param request_args: optional arguments that `request` takes
         :return: A dict containing given URLs as keys, and extracted information as corresponding values.
         """
         results = {}
@@ -142,10 +142,10 @@ def from_urls(urls, timeout=None, user_agent=None):
             pass
         elif len(urls) == 1:
             url = urls[0]
-            html = SimpleCrawler.fetch_url(url, timeout=timeout, user_agent=user_agent)
+            html = SimpleCrawler.fetch_url(url, request_args=request_args)
             results[url] = NewsPlease.from_html(html, url, download_date)
         else:
-            results = SimpleCrawler.fetch_urls(urls, timeout=timeout, user_agent=user_agent)
+            results = SimpleCrawler.fetch_urls(urls, request_args=request_args)
 
             futures = {}
             with cf.ProcessPoolExecutor() as exec:
@@ -158,7 +158,7 @@ def from_urls(urls, timeout=None, user_agent=None):
             for future in cf.as_completed(futures):
                 url = futures[future]
                 try:
-                    results[url] = future.result(timeout=timeout)
+                    results[url] = future.result(timeout=request_args.get("timeout"))
                 except Exception as err:
                     results[url] = {}
 

newsplease/crawler/simple_crawler.py

@@ -28,40 +28,36 @@ class SimpleCrawler(object):
     _results = {}
 
     @staticmethod
-    def fetch_url(url, timeout=None, user_agent=USER_AGENT):
+    def fetch_url(url, request_args=None):
         """
         Crawls the html content of the parameter url and returns the html
         :param url:
-        :param timeout: in seconds, if None, the urllib default is used
+        :param request_args: optional arguments that `request` takes
         :return:
         """
-        return SimpleCrawler._fetch_url(url, False, timeout=timeout, user_agent=user_agent)
+        return SimpleCrawler._fetch_url(url, False, request_args=request_args)
 
     @staticmethod
-    def _fetch_url(url, is_threaded, timeout=None, user_agent=USER_AGENT):
+    def _fetch_url(url, is_threaded, request_args=None):
         """
         Crawls the html content of the parameter url and saves the html in _results
         :param url:
         :param is_threaded: If True, results will be stored for later processing by the fetch_urls method. Else not.
-        :param timeout: in seconds, if None, the urllib default is used
+        :param request_args: optional arguments that `request` takes
         :return: html of the url
         """
-        headers = HEADERS
-        if user_agent:
-            headers["User-Agent"] = user_agent
+        if request_args is None:
+            request_args = {}
+        if "headers" not in request_args:
+            request_args["headers"] = HEADERS
 
         html_str = None
         # send
         try:
             # read by streaming chunks (stream=True, iter_content=xx)
             # so we can stop downloading as soon as MAX_FILE_SIZE is reached
             response = requests.get(
-                url,
-                timeout=timeout,
-                verify=False,
-                allow_redirects=True,
-                headers=headers,
-            )
+                url, verify=False, allow_redirects=True, **request_args)
         except (requests.exceptions.MissingSchema, requests.exceptions.InvalidURL):
             LOGGER.error("malformed URL: %s", url)
         except requests.exceptions.TooManyRedirects:
@@ -91,15 +87,15 @@ def _fetch_url(url, is_threaded, timeout=None, user_agent=USER_AGENT):
         return html_str
 
     @staticmethod
-    def fetch_urls(urls, timeout=None, user_agent=USER_AGENT):
+    def fetch_urls(urls, request_args=None):
         """
         Crawls the html content of all given urls in parallel. Returns when all requests are processed.
         :param urls:
-        :param timeout: in seconds, if None, the urllib default is used
+        :param request_args: optional arguments that `request` takes
         :return:
         """
         threads = [
-            threading.Thread(target=SimpleCrawler._fetch_url, args=(url, True, timeout, user_agent))
+            threading.Thread(target=SimpleCrawler._fetch_url, args=(url, True, request_args))
             for url in urls
         ]
         for thread in threads: