save raw data as json

crawler.py

@@ -3,6 +3,9 @@ import re
 import json
 from bs4 import BeautifulSoup
 from time import sleep
+from os.path import commonprefix
+from os import makedirs
+import argparse
 
 BUNDESTAG_URL = "https://www.bundestag.de/ajax/filterlist/de/abgeordnete/biografien/1040594-1040594?limit=9999&view=BTBiographyList"
 BUNDESTAG_BASE_URL = "https://www.bundestag.de"
@@ -12,6 +15,7 @@ class Biography:
     def __init__(
         self,
         name,
+        party,
         cv,
         speeches,
         votes,
@@ -21,6 +25,7 @@ class Biography:
         disclosures,
     ):
         self.name = name
+        self.party = party
         self.cv = cv
         self.speeches = speeches
         self.votes = votes
@@ -29,22 +34,75 @@ class Biography:
         self.mandate = mandate
         self.disclosures = disclosures
 
+    def __repr__(self):
+        txt = f"""
+name: {self.name}
+party: {self.party}
+cv: {self.cv}
+speeches: {self.speeches}
+votes: {self.votes}
+functions: {self.functions}
+additional_functions: {self.additional_functions}
+mandate: {self.mandate}
+disclosures: {self.disclosures}
+            """
+        return txt
+
+    def to_dict(self):
+        return {
+            "name": self.name,
+            "party": self.party,
+            "cv": self.cv,
+            "speeches": self.speeches,
+            "votes": self.votes,
+            "functions": self.functions,
+            "additional_functions": self.additional_functions,
+            "mandate": self.mandate,
+            "disclosures": self.disclosures,
+        }
+
 
 def main():
+    parser = argparse.ArgumentParser(
+        prog="Bundescrawler",
+        description="Crawls the pages of german representatives and saves the information in a git repository",
+    )
+    parser.add_argument("-o", "--out")
+    parser.add_argument("--debug", action="store_true")
+    args = parser.parse_args()
+    if not args.out:
+        raise ValueError("must supply out directory")
+    try:
+        makedirs(args.out)
+    except FileExistsError:
+        print("Path already exists")
+        pass
     links, names = get_links_and_names()
+    if args.debug:
+        links = links[:5]
+        names = names[:5]
     bios = [get_bio(link, name) for link, name in zip(links, names)]
 
+    save_info(bios, args.out)
+
+
+def save_info(bios, out):
+    with open(f"{out}/raw.json", "w") as raw_file:
+        json.dump([bio.to_dict() for bio in bios], raw_file, indent=2)
+
 
 def get_links_and_names():
     response = requests.get(BUNDESTAG_URL)
     soup = BeautifulSoup(response.content)
     links = [a.get("href") for a in soup.find_all("a")]
-    names = [a.get("title").strip().split("\n\n\n")[0] for a in soup.find_all("a")]
+    names = [a.text.strip().split("\n\n\n") for a in soup.find_all("a")]
 
     return (links, names)
 
 
 def get_bio(url, name):
+    print(name)
+    name, party = name
     print(name)
     name = name.split(", ")
     print(f"Getting {url} for {name[1]} {name[0]}")
@@ -60,7 +118,7 @@ def get_bio(url, name):
         else:
             speech_div = div
     speech = get_ajax(speech_div)
-    speech_infos, speech_titles = parse_speech(speech)
+    speeches = parse_speech(speech)
     vote = get_ajax(vote_div)
     votes = parse_vote(vote)
     function_divs = soup.find_all(class_="m-biography__membership")
@@ -78,28 +136,22 @@ def get_bio(url, name):
     )
     disclosures = soup.find(class_="m-biography__infoDisclaimer").text.strip()
 
-    print(
+    bio = Biography(
         name,
+        party,
         cv,
-        (speech_titles, speech_infos),
+        speeches,
         votes,
         functions,
         additional_functions,
         mandate,
         disclosures,
     )
-    sleep(10)
 
-    return Biography(
-        name,
-        cv,
-        (speech_titles, speech_infos),
-        votes,
-        functions,
-        additional_functions,
-        mandate,
-        disclosures,
-    )
+    print(bio)
+    sleep(1)
+
+    return bio
 
 
 def get_functions(elem):
@@ -124,13 +176,13 @@ def parse_speech(page):
     if not page:
         return (None, None)
     soup = BeautifulSoup(page.content)
-    infos = [s.text for s in soup.find_all(class_="m-biography__speechtitle")]
+    infos = [s.text for s in soup.find_all(class_="m-biography__speechTitle")]
     titles = [
         title.text
         for title in soup.find_all(class_="a-link__label")
         if "--hidden" not in title.get("class")
     ][::2]
-    return (titles, infos)
+    return list(zip(titles, infos))
 
 
 def parse_vote(page):
@@ -160,5 +212,9 @@ def get_ajax(elem):
     return requests.get(url)
 
 
+def common_suffix(strings):
+    return commonprefix([s[::-1] for s in strings])[::-1]
+
+
 if __name__ == "__main__":
     main()